© 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. 30-TRANSCODER-HP
    7. 95112
    Prev
    Next
    INDEX
    Explanations

    Mixed language and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ¢åįķ
    -0.27
     ped
    -0.27
    åİħ
    -0.27
    笳
    -0.26
     center
    -0.25
     late
    -0.25
    æīĩ
    -0.25
    å®ŀæĸ½æĸ¹æ¡Ī
    -0.25
     centr
    -0.24
     Ped
    -0.24
    POSITIVE LOGITS
    nex
    0.29
    __.__
    0.29
     ni
    0.28
    åĶ¬
    0.27
    dden
    0.27
    大çīĩ
    0.26
    .ot
    0.26
    åħ¶éĹ´
    0.26
    éĴ
    0.25
     rc
    0.25
    Activations Density 0.000%

    No Known Activations