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

    Neuronpedia

    APICircuit 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. 72557
    Prev
    Next
    INDEX
    Explanations

    Professional terminology

    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
    	position
    -0.07
    .Step
    -0.07
     Pluto
    -0.07
    いて
    -0.07
    .Executor
    -0.07
     가지고
    -0.07
     Pierre
    -0.06
     DO
    -0.06
    皇帝
    -0.06
    .sys
    -0.06
    POSITIVE LOGITS
    Shar
    0.07
    法定
    0.07
     �
    0.07
     På
    0.07
     =~
    0.06
     notable
    0.06
     figure
    0.06
     serializers
    0.06
     الاثنين
    0.06
    Heavy
    0.06
    Activations Density 0.372%

    No Known Activations