© 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. 24009
    Prev
    Next
    INDEX
    Explanations

    academic

    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
    amba
    -0.28
    -install
    -0.27
    onomies
    -0.27
    åįļçī©
    -0.25
    ishes
    -0.25
    emet
    -0.25
    .inst
    -0.24
    isters
    -0.24
    üm
    -0.24
    åįķä½į
    -0.24
    POSITIVE LOGITS
    éĥ¨
    0.27
    éĥ¨åī¯
    0.26
    éĥ¨ä¸»ä»»
    0.26
     morals
    0.25
    sville
    0.25
    åı¤åħ¸
    0.25
    addy
    0.24
    æĺ¯æĪijåĽ½
    0.24
    举è¡ĮäºĨ
    0.24
    é©°
    0.23
    Activations Density 0.012%

    No Known Activations