© 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. 48102
    Prev
    Next
    INDEX
    Explanations

    Arabic and Urdu names

    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
    æ¾Ħ
    -0.07
    ÙĬÙĩا
    -0.07
    راء
    -0.07
    	TokenName
    -0.07
    èĩ³äºİ
    -0.07
    clo
    -0.07
    ä¸įçķĻ
    -0.07
     fier
    -0.06
     AGE
    -0.06
    Ñģоб
    -0.06
    POSITIVE LOGITS
    è·Łä»ĸ
    0.10
    åĵ¨
    0.10
    æݼ
    0.09
    è®ĵä»ĸ
    0.09
    vertisement
    0.09
    å«Įçĸij
    0.09
    é£İæ°´
    0.09
    å¢
    0.08
    chaft
    0.08
    让ä»ĸ
    0.08
    Activations Density 0.056%

    No Known Activations