© 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. 20-TRANSCODER-HP
    7. 142363
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     option
    -0.29
    promise
    -0.28
    ,options
    -0.28
    éĢī项
    -0.28
     options
    -0.28
     promise
    -0.28
    romise
    -0.27
    rif
    -0.26
    ç¾İçļĦ
    -0.26
     Options
    -0.25
    POSITIVE LOGITS
    вели
    0.24
     cub
    0.24
    ancement
    0.23
    namespace
    0.23
    _Connection
    0.23
    ^K
    0.23
    ITERAL
    0.23
    usters
    0.23
    ä¸ĢåŃĹ
    0.23
     towel
    0.23
    Activations Density 1.182%

    No Known Activations