© 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. 149441
    Prev
    Next
    INDEX
    Explanations

    Tibetan regions

    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
    磶
    -0.29
    olist
    -0.28
     cab
    -0.27
     ver
    -0.27
    ancy
    -0.26
    åįĹéĿŀ
    -0.26
    ĥĿ
    -0.26
     dem
    -0.26
    æĻķ
    -0.26
    Ol
    -0.26
    POSITIVE LOGITS
    ughters
    0.29
     Xi
    0.28
     Kashmir
    0.28
     Tibetan
    0.27
     MAV
    0.26
    soever
    0.25
    itori
    0.25
    è¡£æŁľ
    0.24
    æŃ¥åħ¥
    0.24
    ITOR
    0.24
    Activations Density 0.905%

    No Known Activations