© 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. 109446
    Prev
    Next
    INDEX
    Explanations

    Technical documentation and logs

    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
    éļıä¹ĭ
    -0.27
     REPL
    -0.26
    è¾ħ
    -0.26
     Alive
    -0.26
    çľĭä½ł
    -0.24
    Alive
    -0.24
     cap
    -0.24
    第ä¸Ģ书记
    -0.24
    ForResource
    -0.24
    ystone
    -0.24
    POSITIVE LOGITS
    -tier
    0.27
    åĪĹ
    0.24
    /Branch
    0.24
    mana
    0.24
     tier
    0.23
    -sheet
    0.23
    èĪĽ
    0.23
    lington
    0.23
     sheet
    0.23
    brush
    0.23
    Activations Density 1.083%

    No Known Activations