© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63731
    Prev
    Next
    INDEX
    Explanations

    chapter

    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
    åģļ好
    -0.29
    èµ·æĿ¥
    -0.28
     affirm
    -0.27
     Released
    -0.26
    æĽ´é«ĺ
    -0.25
    å¡
    -0.25
    uen
    -0.25
    亲
    -0.24
    ä¸Ĭåİ»
    -0.24
    æ¯ıéļĶ
    -0.24
    POSITIVE LOGITS
    ç½ĺ
    0.26
    .AD
    0.25
    بارÙĥ
    0.25
    -Israel
    0.24
     imageData
    0.24
    eva
    0.24
     *)"
    0.24
    /DD
    0.24
    çķ¹
    0.24
    æ²Į
    0.23
    Activations Density 2.598%

    No Known Activations