Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 71787
    Prev
    Next
    INDEX
    Explanations

    holder

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ᅦ
    -0.07
     Observatory
    -0.07
     disregard
    -0.07
    և
    -0.06
     يستطيع
    -0.06
     Trên
    -0.06
    发现自己
    -0.06
     vibe
    -0.06
     новых
    -0.06
    ágenes
    -0.06
    POSITIVE LOGITS
     theories
    0.07
     ------------------------------------------------------------------------↵
    0.07
    _BLOCK
    0.07
    sampling
    0.06
    structuring
    0.06
    �
    0.06
     référence
    0.06
    预测
    0.06
    LC
    0.06
    POL
    0.06
    Activations Density 0.001%

    No Known Activations