© 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. 21585
    Prev
    Next
    INDEX
    Explanations

    if followed by a subject

    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
    ä¹ĭæīĢ
    -0.10
    alus
    -0.10
    è¿Ļä¸ĢçĤ¹
    -0.09
    è¿Ļ件äºĭ
    -0.09
    åľ¨çݩ家
    -0.08
    semble
    -0.08
     bev
    -0.08
    建议
    -0.08
    ój
    -0.08
    uka
    -0.08
    POSITIVE LOGITS
    lessly
    0.11
    ä½Ĩä¸įéĻIJäºİ
    0.10
    een
    0.09
    eper
    0.09
    éģµ
    0.09
    èĢ¨
    0.09
    æł¹æľ¬å°±ä¸į
    0.09
    kip
    0.08
    å¿ĥå¾Ĺä½ĵä¼ļ
    0.08
    indo
    0.08
    Activations Density 0.181%

    No Known Activations