© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 78095
    Prev
    Next
    INDEX
    Explanations

    explicit task directives in user prompts, i.e., instructions that assign actions or request detailed content generation.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     methodName
    -0.07
     grado
    -0.07
     INVALID
    -0.07
     Natasha
    -0.07
    ах
    -0.07
     الفلسطينية
    -0.07
     trắng
    -0.07
    �
    -0.07
    每一位
    -0.07
     Johan
    -0.07
    POSITIVE LOGITS
    rawler
    0.08
     dude
    0.07
    umerator
    0.07
     Deployment
    0.07
    Ւ
    0.07
     RL
    0.07
     rental
    0.07
    𝑽
    0.07
    wind
    0.06
    两三
    0.06
    Activations Density 0.144%

    No Known Activations