© 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. 63935
    Prev
    Next
    INDEX
    Explanations

    true

    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
    ffe
    -0.29
    äºī
    -0.26
     Fi
    -0.25
    ÑĦин
    -0.24
     Typeface
    -0.24
    ä¸įåľ¨
    -0.24
    çĶ±äºİ
    -0.24
     Proof
    -0.24
     \/
    -0.24
     Wr
    -0.24
    POSITIVE LOGITS
    æ¾İæ¹ĥæĸ°éĹ»
    0.27
    å¾Ĺ天
    0.26
    aders
    0.26
    åģ¥åº·æĪIJéķ¿
    0.26
    atar
    0.25
     seeded
    0.24
    æĸ°éĹ»åıijå¸ĥ
    0.24
    sal
    0.23
    á»į
    0.23
    chos
    0.23
    Activations Density 10.185%

    No Known Activations