© 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. 97142
    Prev
    Next
    INDEX
    Explanations

    complexity

    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
     Lot
    -0.29
    åıĺ
    -0.28
     seven
    -0.26
     junto
    -0.26
    rowCount
    -0.25
    createQueryBuilder
    -0.25
     Pol
    -0.25
    mask
    -0.25
    issor
    -0.24
    hammer
    -0.24
    POSITIVE LOGITS
    cci
    0.30
    aran
    0.29
    æ¶īåıĬ
    0.27
     involved
    0.26
     present
    0.26
    -performance
    0.25
    Ĥ¨
    0.25
    aru
    0.25
     involving
    0.25
    å¿įåıĹ
    0.25
    Activations Density 0.026%

    No Known Activations