© 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. 22001
    Prev
    Next
    INDEX
    Explanations

    legality

    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
    Negative Logits
    zens
    -0.29
    ting
    -0.27
    enos
    -0.27
     wards
    -0.26
    館
    -0.26
    uss
    -0.26
    ç¬ijè¯Ŀ
    -0.24
     Tunisia
    -0.24
    æģ¼
    -0.24
    (moment
    -0.23
    POSITIVE LOGITS
    è¿Ŀæ³ķ
    0.32
     sworn
    0.29
     illicit
    0.28
    èĩªçĶ±
    0.28
    eel
    0.28
    vel
    0.28
     Pearce
    0.27
    sw
    0.27
     compliant
    0.26
     ende
    0.26
    Activations Density 0.002%

    No Known Activations