© 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. 35-TRANSCODER-HP
    7. 40665
    Prev
    Next
    INDEX
    Explanations

    such

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     as
    -0.92
    ä½ľçĤº
    -0.67
    ä½ľä¸º
    -0.60
     that
    -0.59
     als
    -0.57
    	as
    -0.51
    ãģ¨ãģĹãģ¦
    -0.49
     sebagai
    -0.47
     As
    -0.46
    ä½ľä¸ºä¸Ģ个
    -0.46
    POSITIVE LOGITS
    çĶ¨æĪ·æıIJä¾Ľ
    0.29
    磩
    0.29
    磷
    0.27
    人ä½ĵ
    0.26
    人åĿĩ
    0.25
    æ¤įçī©
    0.25
    æĢ»æķ°
    0.24
    è·Ŀ离
    0.24
    GitHub
    0.24
    telephone
    0.24
    Activations Density 1.339%

    No Known Activations