© 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. 51156
    Prev
    Next
    INDEX
    Explanations

    bookmark and favorite listings

    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
    amel
    -0.09
    æĹ·
    -0.09
    rum
    -0.08
    IGO
    -0.08
    æĸIJ
    -0.08
    deg
    -0.08
     Hag
    -0.08
     retrofit
    -0.08
    缴æĴŃéĹ´
    -0.08
    éķIJ
    -0.08
    POSITIVE LOGITS
    æĶ¶èĹı
    0.16
    éķ¿ä¹ħ
    0.13
     bookmark
    0.13
    æ°¸ä¹ħ
    0.12
    èĩªå·±åĸľæ¬¢
    0.11
     favorite
    0.11
     Bookmark
    0.11
    æľĢåĸľæ¬¢
    0.11
    ç»ı常
    0.11
    à¹Ħว
    0.11
    Activations Density 0.226%

    No Known Activations