© 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. 29405
    Prev
    Next
    INDEX
    Explanations

    fine

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ernal
    -0.27
    akens
    -0.26
    okane
    -0.25
    xFC
    -0.25
    寬
    -0.25
    ç«Ļéķ¿
    -0.24
    sexy
    -0.24
    деÑĤ
    -0.24
    ribbon
    -0.24
    utzer
    -0.24
    POSITIVE LOGITS
    çļĦä¸ĢéĿ¢
    0.28
    fin
    0.28
     Paris
    0.27
    ocity
    0.26
     Ginger
    0.26
    æŁ¥æī¾
    0.26
    ä¹ĺ车
    0.26
    .poster
    0.26
    egra
    0.25
    çħ®
    0.25
    Activations Density 0.429%

    No Known Activations