© 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. 33394
    Prev
    Next
    INDEX
    Explanations

    Nassau County

    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
    質
    -0.10
     subj
    -0.09
    jure
    -0.09
    jam
    -0.08
    ality
    -0.08
    quil
    -0.08
    è´¨æĦŁ
    -0.08
    ifix
    -0.08
    ä¸į该
    -0.08
    istr
    -0.08
    POSITIVE LOGITS
    éĤĪ
    0.10
    oooooooo
    0.09
    éļĻ
    0.09
    è¿IJåĬ¨ä¼ļ
    0.09
    æ±Ĺ
    0.09
    Slim
    0.08
    åºķ线
    0.08
    oooo
    0.08
    ç¾¤å²Ľ
    0.08
    /or
    0.08
    Activations Density 0.003%

    No Known Activations