© 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. 3281
    Prev
    Next
    INDEX
    Explanations

    rigorous / rigor

    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
    sWith
    -0.09
    ction
    -0.09
    -Russian
    -0.09
    el
    -0.09
    ÑĢей
    -0.09
    avig
    -0.08
    aney
    -0.08
    alc
    -0.08
     vener
    -0.08
    olog
    -0.08
    POSITIVE LOGITS
    ously
    0.13
    对å¾ħ
    0.11
    bred
    0.10
    ç»Ĩèĩ´
    0.10
    iously
    0.10
    äºĨåįĬ天
    0.09
    ä¾Ŀæ³ķ追究
    0.09
    æŃ£å¸¸çļĦ
    0.09
    è¨ĢãģĪãģ°
    0.09
     minded
    0.09
    Activations Density 0.011%

    No Known Activations