© 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. 11863
    Prev
    Next
    INDEX
    Explanations

    DO NOT EDIT! followed by code

    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
    çݺ
    -0.09
    çı²
    -0.09
    屿
    -0.08
    lia
    -0.08
    abl
    -0.08
    esser
    -0.08
    æĦļ
    -0.08
    ripper
    -0.08
    rium
    -0.08
    ä¸ļ
    -0.07
    POSITIVE LOGITS
    ering
    0.11
    çªģçł´
    0.10
    ä¸Ģ人
    0.10
    raft
    0.09
    atomic
    0.09
    æİ¥è¿ĩ
    0.09
    æİ¥åıĹäºĨ
    0.09
    _atomic
    0.09
    çĪ½
    0.09
    æĺĻ
    0.08
    Activations Density 0.013%

    No Known Activations