© 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. 22-TRANSCODER-HP
    7. 88585
    Prev
    Next
    INDEX
    Explanations

    second

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»Ģä¹Īäºĭæĥħ
    -0.31
    ä»Ģä¹Īéĥ½
    -0.29
    strument
    -0.27
    dbo
    -0.24
    argout
    -0.23
    .rl
    -0.23
    //(
    -0.23
    Sometimes
    -0.23
     things
    -0.23
    夫å¦ĩ
    -0.23
    POSITIVE LOGITS
    rosis
    0.24
    lus
    0.23
    aggio
    0.23
    ibr
    0.23
    rado
    0.23
    lec
    0.23
    é¦ĸ页
    0.23
     `'
    0.23
    åĽŀéģ¿
    0.23
    湿度
    0.22
    Activations Density 0.007%

    No Known Activations