© 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. 34799
    Prev
    Next
    INDEX
    Explanations

    known for

    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
    à´Ł
    -0.10
    ä¸Ģçľĭ
    -0.10
    æŃ£åĢ¼
    -0.09
     наÑģелениÑı
    -0.09
    ä¸Ģ线
    -0.09
    argins
    -0.09
    缨
    -0.09
    åı¯èĥ½åıijçĶŁ
    -0.09
    æģķ
    -0.09
    æīįæĺ¯
    -0.09
    POSITIVE LOGITS
    è¿Ļä¹Īåģļ
    0.11
    lio
    0.09
    eld
    0.09
    odor
    0.09
     having
    0.09
     being
    0.09
    è¿Ļæł·åģļ
    0.09
    cano
    0.09
    alo
    0.08
    uts
    0.08
    Activations Density 0.048%

    No Known Activations