© 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. 95084
    Prev
    Next
    INDEX
    Explanations

    Scientific/chemical language

    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
    é¾Ħ
    -0.26
    -bed
    -0.26
    Bed
    -0.25
    è·ijæŃ¥
    -0.25
     Bed
    -0.25
    款
    -0.25
    åºĬ
    -0.25
    ntp
    -0.25
    elier
    -0.25
    bed
    -0.24
    POSITIVE LOGITS
    ircuit
    0.29
     relay
    0.28
     Relay
    0.27
    ev
    0.27
    Commission
    0.27
    å§Ķç»Ħç»ĩ
    0.27
     thy
    0.27
     Stream
    0.27
    æĬĺ
    0.26
    Mil
    0.26
    Activations Density 0.891%

    No Known Activations