© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20390
    Prev
    Next
    INDEX
    Explanations

    OpenBSD

    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
    ski
    -0.08
    åı¤ä»£
    -0.08
    inin
    -0.08
    ta
    -0.08
    å¼Ĥè®®
    -0.08
    æī«ä¸Ģ
    -0.08
    èĻļ
    -0.08
    导
    -0.08
    ipop
    -0.08
    åŁºç¡Ģ
    -0.08
    POSITIVE LOGITS
    èĥģ
    0.09
    èĮ±
    0.09
    æĻ¶ä½ĵ
    0.09
    ëĶ°
    0.08
    .Char
    0.08
     domina
    0.08
    ä¸Ģç¬Ķ
    0.08
     Ðijо
    0.08
    ä¸ĢéŨ
    0.08
    ertino
    0.08
    Activations Density 0.017%

    No Known Activations