© 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. 39440
    Prev
    Next
    INDEX
    Explanations

    sage Vishvamitra, Hiranyakashyapu

    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
    æ¸ħæĸ°
    -0.09
    æĸ°é²ľ
    -0.09
    é«ĺå³°æľŁ
    -0.09
    åıijå±ķ壮大
    -0.09
    继ç»Ńä¿ĿæĮģ
    -0.09
    inho
    -0.08
    èĶļ
    -0.08
    é¾Ľ
    -0.08
    æľįåĬ¡åĮº
    -0.08
    æĭĤ
    -0.08
    POSITIVE LOGITS
    æĻºåķĨ
    0.09
    NIL
    0.09
    çİĭåŃIJ
    0.09
    çĸ½
    0.09
    åľ¯
    0.09
    гал
    0.09
    èĩĤ
    0.08
    à¹Ĥà¸Ľà¸£à¸Ķ
    0.08
     dent
    0.08
     contest
    0.08
    Activations Density 0.040%

    No Known Activations