© 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. 25-TRANSCODER-HP
    7. 109343
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è·
    -0.28
     winters
    -0.27
    æĺ¥å¤ı
    -0.26
     spring
    -0.26
    éŃģ
    -0.26
     Saturdays
    -0.25
    æĺ¼å¤ľ
    -0.25
     EÄŁitim
    -0.25
     Adler
    -0.25
    ç£ģ
    -0.24
    POSITIVE LOGITS
    仿
    0.28
    anned
    0.28
    çļĦè§Ĵèī²
    0.27
    Role
    0.27
     role
    0.26
    orraine
    0.25
    role
    0.25
    ç¿»
    0.24
    annel
    0.24
    ä¸Ģç¬ij
    0.24
    Activations Density 0.892%

    No Known Activations