© 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. 53425
    Prev
    Next
    INDEX
    Explanations

    touch or pat

    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
    è±³
    -0.10
    åĸĿæ°´
    -0.09
    è·Į
    -0.09
    /chart
    -0.09
    ή
    -0.08
    ìĺ
    -0.08
    æĦŁåıĹåĪ°äºĨ
    -0.08
    çļĦåľŁåľ°
    -0.08
    æ´¼
    -0.08
    ç¾İå¾·
    -0.08
    POSITIVE LOGITS
    çĤ¹å¤´
    0.11
    touch
    0.08
    ÑĢоÑģÑĤ
    0.08
     rubbing
    0.08
    å°ıéķĩ
    0.08
    parms
    0.08
     Stam
    0.08
    éģŃåĪ°
    0.08
    tb
    0.08
    æĸ°åŁİ
    0.08
    Activations Density 0.021%

    No Known Activations