© 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. 22-TRANSCODER-HP
    7. 112949
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ç»Łè®¡æķ°æį®
    -0.25
    çĤºäºĨ
    -0.25
    inally
    -0.24
    onor
    -0.24
     GetHashCode
    -0.24
    haft
    -0.24
    ibly
    -0.24
    为äºĨ
    -0.23
     hashing
    -0.23
     statistic
    -0.23
    POSITIVE LOGITS
    æİĮ
    0.23
     Rebel
    0.23
    æīĭæĮĩ
    0.23
     chân
    0.23
    åįĬå²Ľ
    0.23
    hea
    0.23
     first
    0.23
     rebel
    0.22
    gesture
    0.22
     Seller
    0.22
    Activations Density 0.002%

    No Known Activations