© 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. 7675
    Prev
    Next
    INDEX
    Explanations

    code, failure to locate something

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
    vv
    -0.27
    ERENCE
    -0.26
     lesbian
    -0.26
    ä¹Łä¸įéĶĻ
    -0.26
     mention
    -0.25
     always
    -0.24
    .Reference
    -0.24
    erÃŃa
    -0.24
     reference
    -0.24
    ä¸įæľį
    -0.24
    POSITIVE LOGITS
    çĿ£å¯Ł
    0.28
    thon
    0.27
    éĴ²
    0.25
    ç³»ç»ŁçļĦ
    0.25
     Cynthia
    0.25
    é¦ĸéĥ½
    0.24
     Therm
    0.24
    çĪĨ
    0.24
    iants
    0.23
    ENTE
    0.23
    Activations Density 0.001%

    No Known Activations