© 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. 22-TRANSCODER-HP
    7. 88266
    Prev
    Next
    INDEX
    Explanations

    south

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    repid
    -0.27
    wüns
    -0.26
    æľªçŁ¥
    -0.26
    åħ·ä½ĵæĥħåĨµ
    -0.26
    ä¸įåıĹ
    -0.24
    chie
    -0.24
    éĹ®é¢ĺæĺ¯
    -0.24
    å·¥ä½ľæĬ¥åijĬ
    -0.24
    aremos
    -0.23
    å¹¿æ³Ľ
    -0.23
    POSITIVE LOGITS
    çģ«åĬĽ
    0.29
    like
    0.27
     Minor
    0.26
    e
    0.25
    come
    0.25
     /*!
    0.24
    å¦Ĥ
    0.24
     labeling
    0.23
    åĽłåħ¶
    0.23
    ,
    0.23
    Activations Density 0.002%

    No Known Activations