© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35616
    Prev
    Next
    INDEX
    Explanations

    responsible for expenses or safety

    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
    羣å¿ĥ
    -0.10
    adir
    -0.09
    è¾īçħĮ
    -0.08
     Bir
    -0.08
    解éĶģ
    -0.08
     recip
    -0.08
    arg
    -0.08
    çļĦä¿¡å¿ĥ
    -0.08
    æĢ»èµĦ产
    -0.08
     اÙĦØ°
    -0.08
    POSITIVE LOGITS
    ingroup
    0.09
    修补
    0.09
    è¶Ĭé«ĺ
    0.09
    ç»ħ
    0.08
    plusplus
    0.08
     Yahoo
    0.08
    ICA
    0.08
    _FALL
    0.08
    =search
    0.08
    èĤĦ
    0.08
    Activations Density 0.146%

    No Known Activations