© 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. 109589
    Prev
    Next
    INDEX
    Explanations

    English

    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
    ounce
    -0.28
    asking
    -0.25
     addAction
    -0.24
    ervised
    -0.24
    geist
    -0.24
    abee
    -0.23
    ost
    -0.23
    opening
    -0.23
    unable
    -0.23
    awning
    -0.23
    POSITIVE LOGITS
    夷
    0.29
    eric
    0.27
    åħ¥
    0.26
    åħ±åĴĮåĽ½
    0.25
    åī¯æł¡éķ¿
    0.25
    ÑĤÑĢен
    0.25
    æĮª
    0.24
     roots
    0.24
    ece
    0.24
    enor
    0.24
    Activations Density 0.326%

    No Known Activations