© 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. 29151
    Prev
    Next
    INDEX
    Explanations

    material

    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
     comp
    -0.27
     pouvoir
    -0.26
    cki
    -0.24
    尺度
    -0.24
    oshi
    -0.24
     pulp
    -0.24
     pivot
    -0.24
    çľ©
    -0.24
    presence
    -0.24
    ACEMENT
    -0.23
    POSITIVE LOGITS
    ist
    0.29
    ienes
    0.29
    åĮħåĽ´
    0.29
    ivor
    0.26
    åĬŀå®ŀäºĭ
    0.25
    esus
    0.25
    å·²ç»ıæĪIJ为
    0.24
    æĹ¶ä»£ä¸ŃåĽ½
    0.23
    æľĢåŁºæľ¬çļĦ
    0.23
    peri
    0.23
    Activations Density 1.852%

    No Known Activations