© 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. 62982
    Prev
    Next
    INDEX
    Explanations

    brought to

    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
    urer
    -0.10
    blind
    -0.09
     subt
    -0.09
    èĩªåıij
    -0.09
    æĹłæīĢ
    -0.09
    ä»İä¸ļ
    -0.09
    大åħ¨
    -0.09
    çĽ²
    -0.09
     blind
    -0.09
    ucci
    -0.08
    POSITIVE LOGITS
    æĪij家
    0.09
    infinity
    0.09
    èIJĥ
    0.08
    ãģŀ
    0.08
    ész
    0.08
    éĽĨä½ĵ
    0.08
    å¹»æĥ³
    0.08
     Karen
    0.08
    强èĢħ
    0.08
    æĵį
    0.08
    Activations Density 0.009%

    No Known Activations