© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 43433
    Prev
    Next
    INDEX
    Explanations

    code/technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĬŁ
    -0.29
    çĻ¾ç§ij
    -0.28
     pert
    -0.27
    меÑĢ
    -0.27
    ä¸Ģç»ı
    -0.26
    pert
    -0.25
    大夫
    -0.25
     subs
    -0.25
    erk
    -0.25
    ming
    -0.24
    POSITIVE LOGITS
    ilateral
    0.33
    ä¼ł
    0.27
    glas
    0.27
    齿
    0.26
     Hubb
    0.26
    ững
    0.25
    uilder
    0.25
     unge
    0.23
     RequestOptions
    0.23
    å®īåħ¨ä¿Ŀéļľ
    0.23
    Activations Density 0.003%

    No Known Activations