© 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. 30-TRANSCODER-HP
    7. 95026
    Prev
    Next
    INDEX
    Explanations

    code and URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ç£ģ
    -0.28
    hung
    -0.27
    æĮ«
    -0.27
    antas
    -0.26
    æ²Ļ
    -0.26
     commission
    -0.25
    venir
    -0.25
    æĢ§åij½
    -0.24
     magnets
    -0.24
     inventor
    -0.23
    POSITIVE LOGITS
    ÑģÑĤв
    0.32
    spiel
    0.29
     wp
    0.29
    wp
    0.29
    为空
    0.28
    è§Ĥ
    0.26
     Rosen
    0.26
     Ole
    0.25
    空
    0.25
    STER
    0.25
    Activations Density 0.101%

    No Known Activations