© 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. 77548
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Ipv
    -0.07
     InvalidArgumentException
    -0.07
     extrav
    -0.06
     Horror
    -0.06
    ☌
    -0.06
    anus
    -0.06
     bee
    -0.06
     Cara
    -0.06
    МА
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    隶属于
    0.08
    IRC
    0.08
    如果我们
    0.07
    自从
    0.07
     ray
    0.07
    ‑
    0.07
     실제
    0.07
    @Injectable
    0.06
    bulk
    0.06
    팹
    0.06
    Activations Density 0.060%

    No Known Activations