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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24408
    Prev
    Next
    INDEX
    Explanations

    cell biology research

    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
    Street
    -0.08
    uning
    -0.07
    -fluid
    -0.07
    Tweet
    -0.07
     lav
    -0.06
     stay
    -0.06
    耕耘
    -0.06
    live
    -0.06
    thumbnails
    -0.06
    Me
    -0.06
    POSITIVE LOGITS
    救援
    0.08
    _nom
    0.07
    兩
    0.07
     hoped
    0.07
     клиент
    0.06
    appro
    0.06
    _CARD
    0.06
    פופ
    0.06
     urgently
    0.06
    Commit
    0.06
    Activations Density 0.079%

    No Known Activations