© 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. 56392
    Prev
    Next
    INDEX
    Explanations

    the

    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
    åĿIJçĿĢ
    -0.27
    ä¸ĥ个
    -0.26
     heels
    -0.26
    æĬĢèĥ½åŁ¹è®Ń
    -0.26
    çŃīæ´»åĬ¨
    -0.26
    æĬł
    -0.26
    äºĶ个
    -0.25
    pip
    -0.25
    æ°©
    -0.25
    å®ŀ践活åĬ¨
    -0.24
    POSITIVE LOGITS
    gef
    0.28
    å¤IJ
    0.28
    ä»
    0.27
    æѦåĻ¨
    0.26
    建çŃijæĿIJæĸĻ
    0.26
    andom
    0.25
     narzÄĻdzi
    0.25
    outil
    0.25
    chine
    0.24
    çĨŁæĤīçļĦ
    0.24
    Activations Density 0.006%

    No Known Activations