© 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. 107112
    Prev
    Next
    INDEX
    Explanations

    hundred

    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
    çļĦ姿æĢģ
    -0.24
    ifice
    -0.24
     Crime
    -0.24
     lÆ°u
    -0.24
     dbg
    -0.23
    sphere
    -0.23
     Debugger
    -0.23
     ÐŀÑģобенно
    -0.23
    ér
    -0.23
    åı¸
    -0.23
    POSITIVE LOGITS
    åĦ¿
    0.30
    hood
    0.27
    hip
    0.26
    ãģªãģĦ
    0.25
    说çļĦæĺ¯
    0.25
     à¹Ĩ
    0.25
    ãģıãĤĭ
    0.25
    en
    0.24
    mand
    0.24
     required
    0.24
    Activations Density 1.309%

    No Known Activations