© 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. 107248
    Prev
    Next
    INDEX
    Explanations

    math and code

    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¤Ħæĸ¹
    -0.28
    ä¸ĢåĽ¢
    -0.28
     \%
    -0.27
     convenience
    -0.27
     completeness
    -0.26
    çĻ¾åĪĨä¹ĭ
    -0.26
    æĸ¹ä¾¿
    -0.26
    çī¢
    -0.25
     meter
    -0.25
    è¯Ģ
    -0.25
    POSITIVE LOGITS
    å°ıç¼ĸä¸Ģèµ·
    0.28
     thinkers
    0.27
     fmap
    0.26
    ä»ĺãģįåIJĪ
    0.26
    endid
    0.26
     trainable
    0.26
    å·Ŀ
    0.25
    thy
    0.25
    å¼ĢæĿ¥
    0.25
    (&:
    0.24
    Activations Density 1.007%

    No Known Activations