© 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. 8640
    Prev
    Next
    INDEX
    Explanations

    flutter

    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
    ystals
    -0.07
     puzzle
    -0.07
    Firestore
    -0.07
     Prepare
    -0.06
     compound
    -0.06
     Mines
    -0.06
    تحق
    -0.06
     접근
    -0.06
    serialize
    -0.06
     Chain
    -0.06
    POSITIVE LOGITS
    探访
    0.07
    !)↵
    0.07
    ()]);↵
    0.07
    .pag
    0.07
    (())↵
    0.07
    	className
    0.07
    举行的
    0.07
    ----</
    0.06
     neben
    0.06
    _goto
    0.06
    Activations Density 0.002%

    No Known Activations