© 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. 130516
    Prev
    Next
    INDEX
    Explanations

    Technical/Data 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
    ...",↵
    -0.30
    åħ»
    -0.28
     Liberties
    -0.27
    æģķ
    -0.25
    ...",
    -0.25
    ä¹Łä¸įæķ¢
    -0.25
     ëĦĺìĸ´
    -0.25
    ...',↵
    -0.24
    âĢ¦"
    -0.24
    éĴ´
    -0.24
    POSITIVE LOGITS
    ikan
    0.29
    æ´Ĺå¹²åĩĢ
    0.28
    æĶ¶éĽĨ
    0.28
    ä¸įä»ħåı¯ä»¥
    0.28
    èĥ½åĬĽå¼º
    0.27
    å¾Ĺ天
    0.26
     collect
    0.26
    åį³åı¯
    0.25
     valide
    0.25
    DF
    0.25
    Activations Density 74.842%

    No Known Activations