© 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. 62303
    Prev
    Next
    INDEX
    Explanations

    unprecedented events

    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
    åģĩ
    -0.10
    ãģ¨ãģ¯ãģĦãģĪ
    -0.10
    HOLDER
    -0.10
    Úĺ
    -0.10
    eut
    -0.10
    á»ĵn
    -0.10
     Grinder
    -0.09
    MemoryWarning
    -0.09
    ENABLE
    -0.09
    ä¸įä¸Ģå®ļ
    -0.09
    POSITIVE LOGITS
    åīįæīĢæľªæľī
    0.09
     pig
    0.09
    ãģ»
    0.09
    ä¹İ
    0.08
    ä¹ĭå¤Ħ
    0.08
    äºī缸
    0.08
    åīįæīĢæľª
    0.08
    RAFT
    0.08
     amounts
    0.08
     ÑĢанее
    0.08
    Activations Density 0.019%

    No Known Activations