© 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. 109218
    Prev
    Next
    INDEX
    Explanations

    back

    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
    Not in Any Lists

    No Comments

    Negative Logits
    genden
    -0.31
     skies
    -0.27
    被èªī
    -0.27
    Grün
    -0.27
    rosse
    -0.27
    è¯įæĿ¡
    -0.25
    COMPARE
    -0.25
    enido
    -0.25
     unbearable
    -0.25
    ä¹ĭæĺŁ
    -0.24
    POSITIVE LOGITS
    ear
    0.27
    å¼Ĥåľ°
    0.25
    ä¸Ĭä¸ĭ
    0.25
    out
    0.25
    look
    0.25
    `
    0.24
    Studio
    0.24
     out
    0.24
     DFA
    0.24
     studio
    0.24
    Activations Density 0.944%

    No Known Activations