© 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. 29109
    Prev
    Next
    INDEX
    Explanations

    Undetermined or questioned items

    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
     mass
    -0.29
     steady
    -0.27
    -même
    -0.25
    èĢģå®ŀ
    -0.25
     append
    -0.24
     ans
    -0.24
     pel
    -0.24
    CLR
    -0.24
    代
    -0.24
     perf
    -0.23
    POSITIVE LOGITS
    æŁ¥çľĭæĽ´å¤ļ
    0.28
    tern
    0.28
    neas
    0.27
    unct
    0.27
    InSection
    0.27
    .words
    0.26
    ikon
    0.26
    isos
    0.26
    NER
    0.26
    æĪIJåĬŁçİĩ
    0.24
    Activations Density 2.280%

    No Known Activations