© 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. 54181
    Prev
    Next
    INDEX
    Explanations

    overriding or replacing content

    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
    æ®Ħ
    -0.09
    è¯Ŀ说
    -0.09
    isis
    -0.09
    ÙħÙĦ
    -0.09
    retval
    -0.09
    recursive
    -0.09
    ä¸įéĻIJ
    -0.09
    ¼
    -0.08
    端æŃ£
    -0.08
    imat
    -0.08
    POSITIVE LOGITS
    lander
    0.11
    iginal
    0.10
    é¹Ĭ
    0.09
    landers
    0.09
    ingly
    0.09
    etch
    0.09
    åİŁæľīçļĦ
    0.09
    ìĤ¬íķŃ
    0.09
    è¦Ĩ
    0.09
     existing
    0.09
    Activations Density 0.037%

    No Known Activations