© 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. 18640
    Prev
    Next
    INDEX
    Explanations

    indicate whether or by

    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
    ctic
    -0.12
    IJ
    -0.10
    oda
    -0.10
    è¯Ŀ说
    -0.10
    fully
    -0.10
     biá»ĥn
    -0.09
    trak
    -0.09
    bla
    -0.09
    åĽłä¸ºå®ĥ
    -0.09
    ries
    -0.08
    POSITIVE LOGITS
    ìĤ¬íķŃ
    0.14
    ively
    0.13
    ¹
    0.11
    éĥĦ
    0.10
    yat
    0.09
    æĻ°
    0.09
     ÑģебÑı
    0.09
    æī¹ç¤º
    0.09
    ä½ķç§į
    0.09
     ÑģÑĤепени
    0.09
    Activations Density 0.040%

    No Known Activations