© 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. 7869
    Prev
    Next
    INDEX
    Explanations

    general articles

    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
    SEQ
    -0.29
    侥幸
    -0.26
    ä¸Ģå¥Ĺ
    -0.26
    ä¸Ľä¹¦
    -0.25
    åŁİå¸Ĥåıijå±ķ
    -0.24
    udden
    -0.24
     SEQ
    -0.24
    \""
    -0.24
     tog
    -0.24
    èĨı
    -0.24
    POSITIVE LOGITS
     blend
    0.29
    peed
    0.27
     blending
    0.25
    æ¦ľæł·
    0.25
    å½±åĵį
    0.24
    è½½
    0.24
     personal
    0.24
    pcl
    0.23
    Krist
    0.23
    Aw
    0.23
    Activations Density 0.000%

    No Known Activations