© 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. 22079
    Prev
    Next
    INDEX
    Explanations

    reporting

    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
    .drop
    -0.30
     drop
    -0.29
    drop
    -0.28
     dro
    -0.28
     begr
    -0.28
    çłĤ
    -0.26
    oret
    -0.25
    æ£ĵ
    -0.25
     Drop
    -0.25
     OFFSET
    -0.25
    POSITIVE LOGITS
    æ°´è´¨
    0.28
    åīĮ
    0.28
    onian
    0.27
     inv
    0.26
     moss
    0.26
     unins
    0.25
    ertype
    0.25
    èīĩ
    0.25
     dispers
    0.25
    éķ¿å¯¿
    0.24
    Activations Density 0.002%

    No Known Activations