© 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. 27-TRANSCODER-HP
    7. 58248
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĤиÑĢов
    -0.27
    缴å±ŀ
    -0.26
    PELL
    -0.26
    éĢĥ
    -0.25
    课
    -0.25
     pager
    -0.25
    æ¼ıæ´ŀ
    -0.25
     Pager
    -0.25
    ä¼Ĭæĸ¯
    -0.25
     поÑĢÑıдке
    -0.25
    POSITIVE LOGITS
    *&
    0.26
     quickly
    0.26
    alic
    0.25
    ioneer
    0.25
    DataContract
    0.25
    çĤ½
    0.24
     Cabinets
    0.24
    alis
    0.23
     governor
    0.23
    -vector
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.