© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53892
    Prev
    Next
    INDEX
    Explanations

    Detecting abbreviations/codes

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĬ½åıĸ
    -0.27
    .ua
    -0.27
     bols
    -0.27
    вÑĥ
    -0.25
    fuse
    -0.25
     thù
    -0.25
    Bear
    -0.25
     mø
    -0.25
    ableView
    -0.24
     fuse
    -0.24
    POSITIVE LOGITS
    lasses
    0.30
     digit
    0.28
    anth
    0.27
    rel
    0.26
    Digit
    0.26
    res
    0.25
    Digits
    0.25
    aN
    0.25
    lient
    0.25
    _();↵
    0.25
    Activations Density 0.008%

    No Known Activations