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. 59406
    Prev
    Next
    INDEX
    Explanations

    :

    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
    	Ext
    -0.07
     pacman
    -0.07
    保养
    -0.07
    .lot
    -0.07
     Doctor
    -0.07
    _sin
    -0.07
    永恒
    -0.07
    	esc
    -0.07
     antivirus
    -0.06
     unserer
    -0.06
    POSITIVE LOGITS
    ʥ
    0.07
     Csv
    0.07
    _CAT
    0.07
    品种
    0.07
    וב
    0.07
    Ǧ
    0.06
    أطفال
    0.06
     receives
    0.06
    _vertices
    0.06
     connaît
    0.06
    Activations Density 0.001%

    No Known Activations