© 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. 32361
    Prev
    Next
    INDEX
    Explanations

    asking a question

    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
    ç»Ļä»ĸ们
    -0.09
    å¹Ĥ
    -0.09
    溯æºIJ
    -0.09
     Wikimedia
    -0.08
    对ä»ĸ们
    -0.08
    ä»ĸ们ä¼ļ
    -0.08
    åıijæī¬
    -0.08
    åĩ½
    -0.08
    aben
    -0.08
    åĽ½åĨħå¤ĸ
    -0.08
    POSITIVE LOGITS
    请æķĻ
    0.12
    寻æ±Ĥ
    0.12
    请æ±Ĥ
    0.12
    æıIJéĹ®
    0.12
    /request
    0.11
    æ±ĤåĬ©
    0.10
    :request
    0.10
    询éĹ®
    0.10
    çļĦä¿¡å¿ĥ
    0.10
    éĹ®
    0.10
    Activations Density 0.530%

    No Known Activations