© 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. 87481
    Prev
    Next
    INDEX
    Explanations

    varied text snippets

    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
    å¾ħ
    -0.28
    ä¹Łå¥½
    -0.27
    ning
    -0.27
    åĨĴ
    -0.26
    工人
    -0.25
    udos
    -0.25
    ä¸į代表
    -0.25
    %=
    -0.23
     Zion
    -0.23
    失
    -0.23
    POSITIVE LOGITS
    ä¸Ģé¢Ĺ
    0.26
    ))->
    0.25
    èĬ±å¼Ģ
    0.24
    第äºĮæī¹
    0.23
    .ResumeLayout
    0.23
    sville
    0.23
    ç±Į
    0.23
    acker
    0.23
     Hall
    0.23
    logfile
    0.23
    Activations Density 0.005%

    No Known Activations