© 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. 30406
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     doch
    -0.28
    ISTIC
    -0.25
    .lock
    -0.24
    chwitz
    -0.24
    avier
    -0.24
    åıĤä¸İ
    -0.24
     domaine
    -0.23
    便åı¯
    -0.23
    lated
    -0.23
     Particip
    -0.23
    POSITIVE LOGITS
    XP
    0.29
    redi
    0.29
    è£Ķ
    0.25
    xp
    0.25
    ç½®
    0.24
    çļĦå¿ĥ
    0.24
    iliation
    0.24
    erk
    0.24
    è¿Ľä¿®
    0.24
    èĬĤçĤ¹
    0.24
    Activations Density 0.340%

    No Known Activations