© 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. 22-TRANSCODER-HP
    7. 111303
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿ĩå¾Ĺ
    -0.32
    è´ŀ
    -0.27
     impunity
    -0.26
     biên
    -0.26
    entic
    -0.26
     retiring
    -0.25
     banged
    -0.25
    éĿĵ
    -0.25
     Dispatch
    -0.24
     Ext
    -0.23
    POSITIVE LOGITS
    以ä¸Ĭ
    0.27
    æŃ£å¼ı
    0.27
     direct
    0.27
    mere
    0.26
    缴æİ¥
    0.26
     general
    0.25
    å¦Ĥ
    0.25
     purely
    0.25
    -archive
    0.25
     resident
    0.25
    Activations Density 0.012%

    No Known Activations