© 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. 10381
    Prev
    Next
    INDEX
    Explanations

    stuck at

    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
    ä¸Ģè¶Ł
    -0.10
    æĢ¥éĢŁ
    -0.10
    åİŁä»¶
    -0.09
    åľ¨å®¶
    -0.09
    è·³åĩº
    -0.09
    ury
    -0.09
    æĮ¤
    -0.09
    èĢ·
    -0.09
    éĢĢè´§
    -0.09
    èĬ®
    -0.09
    POSITIVE LOGITS
     somewhere
    0.10
    6
    0.08
    为æŃ¢
    0.08
    nish
    0.08
    æŃ£å¥½
    0.08
    loo
    0.08
    4
    0.08
    oon
    0.08
     Guild
    0.08
    éĵ¶æ²³
    0.08
    Activations Density 0.100%

    No Known Activations