© 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. 30252
    Prev
    Next
    INDEX
    Explanations

    ovarian

    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
    Inform
    -0.31
    orce
    -0.28
    inous
    -0.27
    Subjects
    -0.27
     inform
    -0.26
     strut
    -0.25
     Inform
    -0.25
    andon
    -0.25
     Strand
    -0.25
    ÑģÑĤÑĢ
    -0.25
    POSITIVE LOGITS
    çĽ¸ä¼¼
    0.30
    bak
    0.28
    engo
    0.28
    缸è¿ij
    0.25
    Ken
    0.24
    ç£Ĭ
    0.24
    ennie
    0.24
     Mold
    0.24
    cott
    0.24
    ductive
    0.24
    Activations Density 2.019%

    No Known Activations