© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51297
    Prev
    Next
    INDEX
    Explanations

    most or usually

    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
    ä¸į论
    -0.09
    _fil
    -0.09
    åľ°ä¸Ń
    -0.09
    好好
    -0.08
    ä¸įç®Ĺ
    -0.08
     Jeffrey
    -0.08
    人类
    -0.08
    äºĨ解ä¸Ģä¸ĭ
    -0.08
    åį¡æĭī
    -0.08
    ERV
    -0.08
    POSITIVE LOGITS
    æŁĦ
    0.09
    åij¶
    0.08
    éĺ³åħī
    0.08
    åĻ¨æĿIJ
    0.08
    æ·Ģç²ī
    0.08
    IVER
    0.08
    åĽ½æľī
    0.08
     Antib
    0.08
    å¾Ĥ
    0.08
    æĻ´
    0.08
    Activations Density 0.076%

    No Known Activations