© 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. 25-TRANSCODER-HP
    7. 107068
    Prev
    Next
    INDEX
    Explanations

    bold

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Suspension
    -0.28
     suspension
    -0.28
     Laur
    -0.26
    æī°
    -0.26
    éħįåģ¶
    -0.26
    æĦıè¯Ĩå½¢æĢģ
    -0.26
     susp
    -0.25
    æĮĤåľ¨
    -0.25
    bsd
    -0.24
    Susp
    -0.24
    POSITIVE LOGITS
    face
    0.33
    -faced
    0.32
    ìĦł
    0.30
    -face
    0.28
    etical
    0.26
    ä¼Ľ
    0.26
    symbol
    0.25
    éĿ¢
    0.25
     contrasts
    0.24
    erson
    0.24
    Activations Density 0.214%

    No Known Activations