© 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. 51058
    Prev
    Next
    INDEX
    Explanations

    including commercial or without limitation

    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
    ä¸Ģå®ļçļĦ
    -0.09
    å§IJ
    -0.09
    大å®Ĺ
    -0.08
    æľīä¸Ģå®ļçļĦ
    -0.08
    ints
    -0.08
    æ»´
    -0.08
    æŃ£ä¹ī
    -0.08
    Representation
    -0.08
    ä¸įå®Į
    -0.08
    åĩłå®¶
    -0.08
    POSITIVE LOGITS
    Isl
    0.09
    å¨ĥ
    0.08
    ajor
    0.08
    æīįæĺ¯çľŁæŃ£
    0.08
    anka
    0.08
    æ£Ĥ
    0.08
    ä¹IJ
    0.08
    åĬ¨æijĩ
    0.08
    _hdl
    0.08
    _ASC
    0.08
    Activations Density 0.066%

    No Known Activations