© 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. 109459
    Prev
    Next
    INDEX
    Explanations

    locations and buildings

    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
    èµ°å»Ĭ
    -0.27
     Pens
    -0.24
    atform
    -0.24
    åIJĬ顶
    -0.24
    CDF
    -0.24
     Quotes
    -0.24
     Intent
    -0.23
    请çĤ¹åĩ»
    -0.23
     corridors
    -0.23
     Donate
    -0.23
    POSITIVE LOGITS
     resides
    0.32
    tober
    0.32
    alon
    0.31
     residing
    0.31
     reside
    0.30
    åıĸåĨ³
    0.26
    enan
    0.25
    åŃĺåľ¨äºİ
    0.25
    imulator
    0.25
    (/[
    0.25
    Activations Density 0.897%

    No Known Activations