© 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. 40609
    Prev
    Next
    INDEX
    Explanations

    expressing gratitude

    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
     much
    -0.88
    much
    -0.86
     Much
    -0.81
    Much
    -0.75
     MUCH
    -0.63
     mucho
    -0.58
     viel
    -0.46
     beaucoup
    -0.31
     muito
    -0.27
     veel
    -0.27
    POSITIVE LOGITS
     nicely
    0.33
    éĥ½ä¼ļæľī
    0.32
    ä¾ĿçĦ¶æĺ¯
    0.32
     many
    0.31
    ä»įæĺ¯
    0.30
    æĺİæľĹ
    0.30
    many
    0.30
     nice
    0.30
    ä»Ģä¹Īæł·
    0.30
     tall
    0.29
    Activations Density 2.409%

    No Known Activations