© 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. 32-TRANSCODER-HP
    7. 43983
    Prev
    Next
    INDEX
    Explanations

    say "digit"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĺİ代
    -0.33
    ãĥ¼ãĥ«
    -0.32
    æĺİæľĿ
    -0.31
    åħĥ
    -0.28
    ur
    -0.26
    Jimmy
    -0.26
    uri
    -0.26
     bob
    -0.25
    åı£
    -0.24
    Ñĥ
    -0.24
    POSITIVE LOGITS
    æ¸ħ
    0.71
    åħī
    0.52
    æ
    0.50
    éģĵ
    0.43
    åĴ¸
    0.42
     æ¸
    0.41
    æ¸ħéĻ¤
    0.40
     cle
    0.39
     clearing
    0.38
     clearance
    0.37
    Activations Density 0.026%

    No Known Activations