© 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. 62914
    Prev
    Next
    INDEX
    Explanations

    Dates and "b" or "d"

    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
    ä½Ĩæĺ¯å¯¹äºİ
    -0.27
    è¿Ļ份
    -0.27
    SError
    -0.26
    åijľ
    -0.26
    setError
    -0.25
    ä¸įæİĴéĻ¤
    -0.24
    ä¸Ģ个éĹ®é¢ĺ
    -0.23
     zij
    -0.23
    ValidationError
    -0.23
    xm
    -0.23
    POSITIVE LOGITS
    å°±è¿ij
    0.27
    å¿ĥåĬ¨
    0.26
    *</
    0.26
    足
    0.25
    }</
    0.25
    ')}}"></
    0.25
    IDER
    0.25
    Unity
    0.25
     Unity
    0.24
    ettle
    0.24
    Activations Density 3.464%

    No Known Activations