© 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. 130233
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
    hole
    -0.29
    Strip
    -0.26
    راء
    -0.25
     getattr
    -0.25
    holes
    -0.25
    èĽĻ
    -0.25
    [:]
    -0.24
    езд
    -0.24
    éķ°
    -0.24
    -times
    -0.24
    POSITIVE LOGITS
    建设åĴĮ
    0.28
    ç®Ĺæĺ¯
    0.26
    åIJijä¸ĭ
    0.26
    å°±å¤Ł
    0.26
     kingdoms
    0.24
    å°±è§īå¾Ĺ
    0.24
    ,UnityEngine
    0.24
    ä½Ĩ对äºİ
    0.24
    crease
    0.24
    ç»ĵæŀĦè°ĥæķ´
    0.23
    Activations Density 1.726%

    No Known Activations