© 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. 36454
    Prev
    Next
    INDEX
    Explanations

    outcome or final result

    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
    èĵĦ
    -0.09
    æĭİ
    -0.09
    æѤæŶ
    -0.09
    ä½łä»¥ä¸º
    -0.09
    éªł
    -0.09
    vic
    -0.08
    æݥ触åĪ°
    -0.08
    å¹³æŶ
    -0.08
    æѦè£ħ
    -0.08
    å½ĵåģļ
    -0.08
    POSITIVE LOGITS
    æľĢç»Ī
    0.14
     eventual
    0.12
    没èĥ½
    0.11
    æľĢçµĤ
    0.10
    åIJİæĿ¥
    0.10
     eventually
    0.10
     ultimately
    0.10
     ÑĥÑģпеÑĪно
    0.09
     ê²°êµŃ
    0.09
    å¦ĤæľŁ
    0.09
    Activations Density 0.057%

    No Known Activations