© 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. 109196
    Prev
    Next
    INDEX
    Explanations

    which where

    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
    (now
    -0.28
     now
    -0.27
    å°±æĺ¯åľ¨
    -0.26
    è¿ĻæĿ¡
    -0.25
    åħ¶å®ŀå°±æĺ¯
    -0.24
    åı¯åľ¨
    -0.24
    dddd
    -0.24
    [at
    -0.24
    代çIJĨ
    -0.24
    æѤæ¡Ī
    -0.24
    POSITIVE LOGITS
    vents
    0.28
    éĺľ
    0.26
    __))
    0.26
    orr
    0.25
    ieties
    0.25
    isted
    0.24
    cope
    0.24
    ingu
    0.24
    imentos
    0.23
    缸çĪ±
    0.23
    Activations Density 1.049%

    No Known Activations