© 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. 11045
    Prev
    Next
    INDEX
    Explanations

    Adam Lanza

    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
    hift
    -0.09
     заказ
    -0.09
    ities
    -0.09
    举
    -0.08
    itted
    -0.08
    æĹħ游èµĦæºIJ
    -0.08
    åı²è¯Ĺ
    -0.08
     getC
    -0.08
     paced
    -0.08
    _MA
    -0.08
    POSITIVE LOGITS
    å¯Ł
    0.10
    æī¿åĬŀ
    0.09
    elic
    0.09
    æĵ¢
    0.09
    åľ¨ä¹İ
    0.09
     barr
    0.08
    xing
    0.08
    æı¡
    0.08
     Barr
    0.08
    éĵŁ
    0.08
    Activations Density 0.020%

    No Known Activations