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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 111177
    Prev
    Next
    INDEX
    Explanations

    Formal and technical descriptions

    np_max-act · gemini-2.0-flash
    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
    .clear
    -0.07
     reported
    -0.07
    ников
    -0.07
     APPLICATION
    -0.07
     bevor
    -0.07
    achsen
    -0.07
     lol
    -0.06
     qualidade
    -0.06
     rival
    -0.06
    loomberg
    -0.06
    POSITIVE LOGITS
     Lo
    0.08
    𝑤
    0.07
    �件
    0.07
     craz
    0.07
     nails
    0.07
     marsh
    0.07
    更好的
    0.07
    给予
    0.06
     Shen
    0.06
     Sabb
    0.06
    Activations Density 0.397%

    No Known Activations