© 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. 22172
    Prev
    Next
    INDEX
    Explanations

    0

    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
     hier
    -0.29
    çł»
    -0.27
     Walters
    -0.26
     raises
    -0.26
    ent
    -0.26
     release
    -0.24
    enter
    -0.24
     авгÑĥÑģÑĤа
    -0.24
     unrest
    -0.24
    ervers
    -0.24
    POSITIVE LOGITS
    [assembly
    0.27
    зон
    0.26
     strapped
    0.26
    -budget
    0.26
     pronounce
    0.25
     honeymoon
    0.25
    omaly
    0.25
    èµ°ä¸ĭåİ»
    0.25
    ĶåĽŀ
    0.25
    çIJĨäºĭä¼ļ
    0.25
    Activations Density 0.002%

    No Known Activations