© 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. 33-TRANSCODER-HP
    7. 54791
    Prev
    Next
    INDEX
    Explanations

    geographical locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    erd
    -0.33
    sd
    -0.32
    æŃĮ
    -0.31
    erie
    -0.31
    eo
    -0.28
    iac
    -0.28
    ean
    -0.27
    (sd
    -0.27
     chamber
    -0.27
    ierz
    -0.27
    POSITIVE LOGITS
    zet
    0.27
    åħ¨åľº
    0.26
     Peg
    0.25
    -quote
    0.25
    åĽ½éĺ²
    0.24
     paddingHorizontal
    0.23
     zenith
    0.23
     fiat
    0.23
    .toObject
    0.23
    izar
    0.23
    Activations Density 0.015%

    No Known Activations