© 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. 24-TRANSCODER-HP
    7. 151056
    Prev
    Next
    INDEX
    Explanations

    grains and brewing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ¸ł
    -0.26
    itives
    -0.26
    ragment
    -0.25
    ië
    -0.24
    semicolon
    -0.24
    equality
    -0.24
    agents
    -0.24
    æ¡IJ
    -0.24
    mission
    -0.24
    missions
    -0.24
    POSITIVE LOGITS
     reduction
    0.28
    åIJįçīĩ
    0.25
     manufactured
    0.25
     manufacture
    0.24
    -maker
    0.24
    æµĨ
    0.24
     chorus
    0.24
    oup
    0.23
    Je
    0.23
     (++
    0.23
    Activations Density 0.312%

    No Known Activations