© 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. 30971
    Prev
    Next
    INDEX
    Explanations

    surname or given name

    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
    æīĵåĮħ
    -0.10
    ä¸ĭçıŃ
    -0.09
    åĬŀ好
    -0.09
    çĻĤ
    -0.08
    人身
    -0.08
    å¦ĸ
    -0.08
    abeth
    -0.08
    çĤ¸
    -0.08
    åĴĮæĶ¯æĮģ
    -0.08
    ienen
    -0.08
    POSITIVE LOGITS
    å§ĵ
    0.10
    CCR
    0.09
    uell
    0.09
    åIJįä¹ī
    0.09
    夹
    0.09
    ä¹īä¹Į
    0.08
    å²Ĺ
    0.08
    ErrorException
    0.08
     penn
    0.08
    ekt
    0.08
    Activations Density 0.157%

    No Known Activations