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. 48434
    Prev
    Next
    INDEX
    Explanations

    Describing species

    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
    ToJson
    -0.07
    �
    -0.07
    $objPHPExcel
    -0.07
     transl
    -0.07
    暮
    -0.07
    .copyWith
    -0.07
    .Patient
    -0.06
    (tcp
    -0.06
    .listen
    -0.06
    .go
    -0.06
    POSITIVE LOGITS
     awarded
    0.07
     semanas
    0.07
     reunion
    0.07
     announce
    0.07
    imals
    0.07
    ديد
    0.07
    队
    0.07
     المتحدة
    0.06
    )<<
    0.06
    boost
    0.06
    Activations Density 0.018%

    No Known Activations