© 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. 151257
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
    Negative Logits
    大大
    -0.30
    å½¢åĬ¿
    -0.28
    acles
    -0.26
    æĥħåĨµ
    -0.26
    å®ŀåľ¨
    -0.26
    ation
    -0.26
     impuls
    -0.25
     instantaneous
    -0.25
    æłijæŀĿ
    -0.25
    主æĦı
    -0.25
    POSITIVE LOGITS
    ucken
    0.29
     TOK
    0.27
    éĢĢ
    0.26
    INESS
    0.26
    ãģįãģ¦
    0.25
    #",
    0.25
    -dat
    0.24
    ombine
    0.24
    礼
    0.24
    æīĭèħķ
    0.24
    Activations Density 0.915%

    No Known Activations