© 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. 20-TRANSCODER-HP
    7. 140843
    Prev
    Next
    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ±ĤåĬ©
    -0.33
    解åĨ³
    -0.33
    对çŃĸ
    -0.32
    为äºĨéģ¿åħį
    -0.32
     correcting
    -0.32
    ç¼ĵ解
    -0.32
    åĪ¶æŃ¢
    -0.31
    æ¶ĪéĻ¤
    -0.31
    解決
    -0.30
    ä½ıåĿĢ
    -0.30
    POSITIVE LOGITS
    èĥ´
    0.27
    奥迪
    0.25
     clone
    0.25
     sure
    0.25
    岿
    0.25
    ªĮ
    0.24
    De
    0.24
    æ³ķå¾ĭæ³ķè§Ħ
    0.24
    åħ±çĶŁ
    0.24
    Microsoft
    0.24
    Activations Density 66.694%

    No Known Activations