© 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. 27213
    Prev
    Next
    INDEX
    Explanations

    boutique

    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
    /or
    -0.09
    ilog
    -0.09
    fully
    -0.09
    ç¿Ģ
    -0.09
    æĮ¯åħ´
    -0.09
    ÙĪØ·
    -0.08
    akan
    -0.08
     dawn
    -0.08
     plano
    -0.08
     ÙĤض
    -0.08
    POSITIVE LOGITS
    ues
    0.12
    åĮĸçļĦ
    0.11
    iliary
    0.11
    ÙĬÙĩ
    0.09
    orris
    0.09
    èµ°å¾Ĺ
    0.09
    è·Ľ
    0.09
    æļ¹
    0.09
    iali
    0.09
    çĭİ
    0.09
    Activations Density 0.002%

    No Known Activations