© 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. 130530
    Prev
    Next
    INDEX
    Explanations

    .

    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
    ä¹Łåı¯èĥ½
    -0.32
    urg
    -0.30
    ä¹Łå¼Ģå§ĭ
    -0.27
     Similarly
    -0.27
    Similarly
    -0.26
    Cause
    -0.26
    ä¹Łæĺ¯å¦ĤæѤ
    -0.26
    begin
    -0.26
     {}.
    -0.25
     similarly
    -0.25
    POSITIVE LOGITS
    ANE
    0.31
    ẫu
    0.28
    _agg
    0.28
    ousy
    0.28
    _recent
    0.27
     recent
    0.27
    mpz
    0.26
    anon
    0.26
    agree
    0.26
     recently
    0.25
    Activations Density 0.008%

    No Known Activations