© 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. 4459
    Prev
    Next
    INDEX
    Explanations

    effort put into

    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
    paired
    -0.09
    ç½®
    -0.09
    é¦ĸå¸Ń
    -0.09
    线ä¸ĭ
    -0.08
    pow
    -0.08
    icken
    -0.08
    éĿŀ常好çļĦ
    -0.08
    okia
    -0.08
    alion
    -0.08
    å½ĵä¹ĭæĹłæĦ§
    -0.08
    POSITIVE LOGITS
    æĬķåħ¥
    0.14
     into
    0.13
    Into
    0.12
    å¿ĥè¡Ģ
    0.12
    _into
    0.12
    è¿Ľåİ»
    0.11
    æĬķåħ¥åĪ°
    0.11
     vÃło
    0.11
    alem
    0.11
     effort
    0.11
    Activations Density 0.058%

    No Known Activations