© 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. 33149
    Prev
    Next
    INDEX
    Explanations

    to [duration/time/action]

    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
    icus
    -0.11
    åĩłæ¬¡
    -0.10
     recognizer
    -0.10
    æĥ³åĥı
    -0.09
    riere
    -0.09
    _NC
    -0.09
    æĹ©
    -0.09
    FIN
    -0.09
    åºķå±Ĥ
    -0.09
    ä½ķ度
    -0.08
    POSITIVE LOGITS
    ope
    0.09
    ä¼ı
    0.09
    ä¿ĿæĮģçĿĢ
    0.09
    нак
    0.09
    尤为
    0.08
    åѦä¼ļ
    0.08
    å±ķå¼Ģ
    0.08
    ableObject
    0.08
    ç«Ļåľ¨
    0.08
    åѦä¼ļäºĨ
    0.08
    Activations Density 0.018%

    No Known Activations