© 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. 24-TRANSCODER-HP
    7. 151149
    Prev
    Next
    INDEX
    Explanations

    academic papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    宫
    -0.33
    æĤ£åĦ¿
    -0.31
     patients
    -0.30
    .Patient
    -0.30
    æĤ£èĢħ
    -0.30
     patient
    -0.29
     clinical
    -0.28
     Patient
    -0.28
     Patients
    -0.28
    æĤ£èĢħçļĦ
    -0.28
    POSITIVE LOGITS
    ç¦ıå¾·
    0.29
     Zo
    0.25
    è§Ĥ
    0.25
    æĺŃ
    0.25
     Mathf
    0.25
    åı¤äºº
    0.25
     cork
    0.24
    ILED
    0.24
    oned
    0.23
    é¢Ĩ导çıŃåŃIJ
    0.23
    Activations Density 1.227%

    No Known Activations