© 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. 21472
    Prev
    Next
    INDEX
    Explanations

    patent invention or music chords

    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
    åIJīä»ĸ
    -0.11
    ç®±åŃIJ
    -0.10
    æīĭæĦŁ
    -0.10
    éĶ®çĽĺ
    -0.09
    åĭ¤
    -0.09
    æĸ«
    -0.09
    èħķ
    -0.09
    latent
    -0.09
    éŀ£
    -0.08
    lat
    -0.08
    POSITIVE LOGITS
    éĹ¹
    0.10
    åĿIJ
    0.09
    带头
    0.09
    åī©
    0.08
    ulen
    0.08
    大åݦ
    0.08
     bip
    0.08
     Oswald
    0.08
    óa
    0.08
    æĢĿ
    0.08
    Activations Density 0.018%

    No Known Activations