© 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. 9-TRANSCODER-HP
    7. 29350
    Prev
    Next
    INDEX
    Explanations

    school

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     decimal
    -0.28
    forth
    -0.27
     intermediate
    -0.26
    enti
    -0.26
    åľ¨è¿ĩ渡
    -0.26
     distributors
    -0.24
    èĪĮ
    -0.24
    çļ®èĤ¤çĹħ
    -0.24
    idente
    -0.24
     cams
    -0.24
    POSITIVE LOGITS
    ojis
    0.32
    èĩªæĦ¿
    0.28
    人们对
    0.26
    èĦĨ
    0.26
     volunt
    0.26
     PD
    0.25
    Rated
    0.25
    PD
    0.25
     vol
    0.25
     \"$
    0.25
    Activations Density 0.371%

    No Known Activations