© 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. 32-TRANSCODER-HP
    7. 44115
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éĻ¢
    -0.31
    åѤ
    -0.30
    verages
    -0.28
    anford
    -0.26
    concert
    -0.26
    æĢĴ
    -0.25
    å¤ĸéĥ¨
    -0.25
    çĶ·ä¸»è§Ĵ
    -0.25
    icity
    -0.24
    èľľ
    -0.24
    POSITIVE LOGITS
    oda
    0.28
    EEK
    0.27
     Sunshine
    0.27
     Sync
    0.27
    :relative
    0.26
    ALE
    0.26
    .Sync
    0.26
     Pen
    0.25
     Le
    0.25
    ERO
    0.25
    Activations Density 0.001%

    No Known Activations