© 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. 110939
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    åħĥ
    -0.26
    rub
    -0.25
    owa
    -0.25
    好å¥ĩå¿ĥ
    -0.24
    .ol
    -0.24
    yu
    -0.23
     CP
    -0.23
    abin
    -0.23
     optional
    -0.22
     owe
    -0.22
    POSITIVE LOGITS
    icular
    0.30
    enate
    0.26
    chers
    0.25
    baugh
    0.25
    vak
    0.24
    adle
    0.24
    ä¸įè§ģ
    0.24
    .raise
    0.24
    ining
    0.23
    amation
    0.23
    Activations Density 0.359%

    No Known Activations