© 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. 36150
    Prev
    Next
    INDEX
    Explanations

    in strict accordance

    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
    ibu
    -0.08
    æī¿
    -0.08
    æľīä¸Ģä½į
    -0.08
    ä¸İåħ¶
    -0.08
    è¾ħ
    -0.08
    æĺ¯ä¸Ģä½į
    -0.08
    ç»Ĵ
    -0.07
    æľĿ
    -0.07
     elabor
    -0.07
     afford
    -0.07
    POSITIVE LOGITS
    Reporter
    0.09
    åĽŀèIJ½
    0.09
    æķĻä½ł
    0.09
    ppy
    0.09
    æݨåIJij
    0.09
    åŁºç¡Ģä¸Ĭ
    0.09
    erable
    0.09
    æij½
    0.08
     CHRIST
    0.08
    ï¹ĥ
    0.08
    Activations Density 0.133%

    No Known Activations