© 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. 35-TRANSCODER-HP
    7. 40789
    Prev
    Next
    INDEX
    Explanations

    say "the ending -ary"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çħ¤çĤŃ
    -0.31
    translations
    -0.30
    ä¸īæĿ¡
    -0.27
    两款
    -0.26
     Politico
    -0.26
    èģĮå·¥
    -0.26
    éĿ¢èī²
    -0.26
    [arr
    -0.26
    ircles
    -0.26
    plers
    -0.25
    POSITIVE LOGITS
    rab
    0.46
    a
    0.42
    race
    0.38
    rain
    0.37
    rai
    0.35
    agi
    0.35
    rium
    0.34
    raj
    0.34
    asy
    0.33
    obi
    0.33
    Activations Density 0.084%

    No Known Activations