© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 22290
    Prev
    Next
    INDEX
    Explanations

    sent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĮ¯
    -0.30
    oria
    -0.28
    é¢ĺ
    -0.26
     fragmentation
    -0.25
    amon
    -0.25
    asion
    -0.24
     alloys
    -0.24
    ç¢İ
    -0.24
    çŃĶå¤į
    -0.24
    MA
    -0.23
    POSITIVE LOGITS
    å½±
    0.27
    èĩ´
    0.26
    濯
    0.26
     Dut
    0.26
     Barrel
    0.25
    (({
    0.25
     Lob
    0.24
    Ïĭ
    0.24
    _NR
    0.24
     ICU
    0.23
    Activations Density 0.000%

    No Known Activations