© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 17253
    Prev
    Next
    INDEX
    Explanations

    formats for media and signals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    好åIJĥ
    -0.10
    .TabIndex
    -0.09
    inar
    -0.09
    ä¸įçĶ±
    -0.09
    ypi
    -0.09
    æĮĩæľĽ
    -0.08
    éľ¾
    -0.08
    å´ĩé«ĺ
    -0.08
    é²ľèĬ±
    -0.08
    æľ¦èĥ§
    -0.08
    POSITIVE LOGITS
    ç©¿è¿ĩ
    0.09
     Anthem
    0.09
    è¿ĻæĿ¡
    0.09
    èĤĦ
    0.09
    _primitive
    0.09
    ç®IJ
    0.09
    åIJĵå¾Ĺ
    0.09
    ç½ijç»ľä¼łæĴŃ
    0.09
    primitive
    0.08
    å´ĸ
    0.08
    Activations Density 0.112%

    No Known Activations