© 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. 96882
    Prev
    Next
    INDEX
    Explanations

    by

    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
    æ½ĩ
    -0.29
    好åIJĹ
    -0.26
    çīº
    -0.25
     chuck
    -0.25
    è¿ĻçĤ¹
    -0.25
     billboard
    -0.25
    ukkan
    -0.24
    \Configuration
    -0.24
    缴æµģ
    -0.24
    dle
    -0.24
    POSITIVE LOGITS
     cold
    0.27
    åĨ·
    0.27
    aeda
    0.26
     storm
    0.25
    å·²ç»ı被
    0.25
    izu
    0.25
    rtle
    0.25
     Course
    0.25
    çģ¶
    0.24
     Hour
    0.24
    Activations Density 0.003%

    No Known Activations