© 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. 107299
    Prev
    Next
    INDEX
    Explanations

    God

    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
    å´ĩæĭľ
    -0.27
    verter
    -0.27
    éĻį温
    -0.26
    建设åĴĮ
    -0.26
    å°¼äºļ
    -0.25
    è®¤çľŁåŃ¦ä¹ł
    -0.25
    onta
    -0.25
    å¢ĥ
    -0.25
    lessly
    -0.25
     living
    -0.24
    POSITIVE LOGITS
    驸
    0.27
    .setSelection
    0.27
    ourney
    0.25
    Sexy
    0.24
    .setTag
    0.24
    attern
    0.24
    éĴĿ
    0.24
     SEX
    0.24
     Girlfriend
    0.24
    æīĢæīĢéķ¿
    0.24
    Activations Density 0.123%

    No Known Activations