© 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. 23-TRANSCODER-HP
    7. 23568
    Prev
    Next
    INDEX
    Explanations

    keep

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éĻī
    -0.29
    æŁłæª¬
    -0.28
    ä¼ij
    -0.28
    prefer
    -0.28
     Scotch
    -0.26
    æĥ§
    -0.26
    就没æľī
    -0.25
     chance
    -0.25
    by
    -0.25
    åħ³æ³¨
    -0.25
    POSITIVE LOGITS
    æĹ¥æĬ¥éģĵ
    0.27
    essler
    0.27
    åı·çº¿
    0.26
    modelName
    0.25
    izo
    0.25
     çe
    0.25
     illustrate
    0.24
    cket
    0.24
    ocz
    0.24
     unins
    0.24
    Activations Density 0.006%

    No Known Activations