© 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. 142590
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    Negative Logits
    åıijéĢģ
    -0.26
    INED
    -0.26
     catch
    -0.26
    catch
    -0.26
    uc
    -0.25
    éĴİ
    -0.25
    è¿Ļåı¥è¯Ŀ
    -0.24
    anic
    -0.24
    主ä½ĵ
    -0.24
    unch
    -0.24
    POSITIVE LOGITS
    &type
    0.32
    stype
    0.28
    dataType
    0.27
    æŁ´
    0.26
     delt
    0.25
     separate
    0.25
    âĢ¦”
    0.24
     ..."↵↵
    0.23
     TokenType
    0.23
     setType
    0.23
    Activations Density 0.490%

    No Known Activations