© 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. 107028
    Prev
    Next
    INDEX
    Explanations

    rud

    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
    -corner
    -0.27
    -ret
    -0.26
     ret
    -0.26
     ca
    -0.25
    [count
    -0.25
     onPage
    -0.25
    åı£æ°´
    -0.24
    -side
    -0.24
    ĶåĽŀ
    -0.24
    èĥ½åIJ¦
    -0.24
    POSITIVE LOGITS
    imentary
    0.33
    æ¯Ľ
    0.31
    isper
    0.29
    бÑĢи
    0.27
     fashioned
    0.26
    积æŀģ
    0.25
    istic
    0.25
    iment
    0.25
    gest
    0.25
     Brushes
    0.25
    Activations Density 0.116%

    No Known Activations