© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 23952
    Prev
    Next
    INDEX
    Explanations

    instructions/providing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dese
    -0.29
    æݨèįIJ
    -0.27
    [((
    -0.26
    æݨèĸ¦
    -0.26
     remark
    -0.25
    缮
    -0.25
     steward
    -0.25
     возд
    -0.25
    çĿģå¼Ģ
    -0.24
    Ử
    -0.24
    POSITIVE LOGITS
     Mutual
    0.28
    rompt
    0.26
    hide
    0.26
    æĦĪ
    0.25
    iland
    0.25
     amore
    0.25
    æ°´èµĦæºIJ
    0.24
    mask
    0.24
     Plants
    0.24
     bom
    0.24
    Activations Density 0.002%

    No Known Activations