© 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. 109288
    Prev
    Next
    INDEX
    Explanations

    say number 0

    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
    åĹĿ
    -0.27
    ä¸ĩ亿
    -0.27
     $('#'
    -0.27
    sson
    -0.26
    åIJ¬è¯´è¿ĩ
    -0.25
    强奸
    -0.25
    opard
    -0.24
    æĩ·
    -0.24
     univers
    -0.24
    ount
    -0.24
    POSITIVE LOGITS
    tol
    0.28
    æľĢé«ĺ
    0.28
    èĢIJ
    0.27
    вÑĭ
    0.26
    ä»»æĢ§
    0.26
    session
    0.26
    ersed
    0.26
    ering
    0.26
    éĢIJ
    0.26
    atis
    0.25
    Activations Density 0.914%

    No Known Activations