© 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. 1467
    Prev
    Next
    INDEX
    Explanations

    references and mentions

    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
    urm
    -0.09
    端æŃ£
    -0.08
     Ches
    -0.08
    é±¼
    -0.08
    _ang
    -0.08
    æ´ij
    -0.07
    ä»Ķ
    -0.07
    æĻļå¹´
    -0.07
    åIJ¬äºĨ
    -0.07
     tad
    -0.07
    POSITIVE LOGITS
    æıIJåıĬ
    0.12
    åİĨåı²æĢ§
    0.11
    reference
    0.11
     references
    0.10
     mention
    0.10
    åĹĿ
    0.10
     mentions
    0.10
    åŁºåĩĨ
    0.10
    æıIJåĪ°
    0.10
     reference
    0.10
    Activations Density 0.123%

    No Known Activations