© 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. 109574
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
    Negative Logits
    ugu
    -0.26
     EXISTS
    -0.25
    ries
    -0.24
    éĨĴ缮
    -0.24
    contrast
    -0.24
    itra
    -0.24
    jac
    -0.23
    è®®äºĭ
    -0.23
     ATTACK
    -0.23
    queda
    -0.23
    POSITIVE LOGITS
    ullet
    0.25
    digest
    0.25
     digest
    0.25
     thro
    0.23
    stand
    0.23
    ä¼łæŁĵ
    0.23
     Plat
    0.23
    æŶæĬ¥
    0.23
    NAV
    0.23
    åĪ·
    0.23
    Activations Density 0.050%

    No Known Activations