© 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. 19-RESID-POST-AA
    6. 5870
    Prev
    Next
    INDEX
    Explanations

    situation

    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
     eldre
    -0.08
    (pe
    -0.08
    三千
    -0.07
    ToDelete
    -0.07
    .getM
    -0.07
    =search
    -0.07
    addChild
    -0.07
    _release
    -0.07
    oler
    -0.07
     amendment
    -0.07
    POSITIVE LOGITS
     situated
    0.10
     situation
    0.08
    情况
    0.08
     situations
    0.08
    кат
    0.07
    情况进行
    0.07
     situación
    0.07
    套路
    0.07
     постоянн
    0.07
    tığını
    0.07
    Activations Density 0.028%

    No Known Activations