© 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. 19349
    Prev
    Next
    INDEX
    Explanations

    bromeliad, usually stick

    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
    Pairs
    -0.09
    é¢Ħè§ģ
    -0.09
    裸
    -0.08
    ä¿ij
    -0.08
    汤
    -0.08
    湯
    -0.08
    ç¨ļ
    -0.08
    çĦ°
    -0.08
    UME
    -0.08
    è±Į
    -0.08
    POSITIVE LOGITS
     palms
    0.09
    èĭ¹
    0.09
     sto
    0.08
    åĿª
    0.08
    çĮ®
    0.08
    æĺİçıł
    0.08
    ä½ķåĨµ
    0.08
    ç»Ī身
    0.08
    GLOBALS
    0.08
    磼
    0.08
    Activations Density 0.046%

    No Known Activations