© 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. 149161
    Prev
    Next
    INDEX
    Explanations

    force

    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
    Negative Logits
    åįłçĶ¨
    -0.28
     warmer
    -0.27
    izard
    -0.27
    iliate
    -0.26
     warmth
    -0.25
    å±IJ
    -0.24
     brighter
    -0.24
     Hil
    -0.24
    é¦ij
    -0.24
    -php
    -0.24
    POSITIVE LOGITS
     exert
    0.30
    平衡
    0.30
    èĩĤ
    0.29
    olla
    0.29
    BAL
    0.29
     Factor
    0.29
     balance
    0.29
     Forces
    0.28
    ä½ĵåĬĽ
    0.28
     Force
    0.28
    Activations Density 1.187%

    No Known Activations