© 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. 54691
    Prev
    Next
    INDEX
    Explanations

    say "V" words

    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
    士åħµ
    -0.28
    pac
    -0.27
    ä¸įå¿ĺ
    -0.26
    igators
    -0.26
    ç¾İåĨĽ
    -0.26
    æĪĺ士
    -0.26
    worthy
    -0.26
    RestController
    -0.25
    æĪĺçģ«
    -0.25
    å¸Ń
    -0.25
    POSITIVE LOGITS
    ard
    0.27
    é£İ
    0.26
     writable
    0.25
    brick
    0.25
    Ĥ¤
    0.24
     void
    0.24
    空çĻ½
    0.24
    ippo
    0.24
    elim
    0.23
     black
    0.23
    Activations Density 0.007%

    No Known Activations