© 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. 19564
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
    2
    -0.09
    森
    -0.09
    æĭ¿åĪ°
    -0.09
    ä¸įå±ij
    -0.09
    NECT
    -0.09
    eeper
    -0.09
    åŁºæľ¬ä¸Ĭ
    -0.09
    æĭ¿åĪ°äºĨ
    -0.09
    3
    -0.08
    ailable
    -0.08
    POSITIVE LOGITS
    ä¸Ģä¼ļ
    0.09
    rence
    0.09
    åªļ
    0.09
    akh
    0.08
    uria
    0.08
    éĽ¾
    0.08
    ä¿®æŃ£
    0.08
    ithe
    0.08
    opsis
    0.08
    elic
    0.08
    Activations Density 0.028%

    No Known Activations