© 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. 58086
    Prev
    Next
    INDEX
    Explanations

    population counts and details

    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
    æ½ĩæ´Ĵ
    -0.09
    æģ¤
    -0.08
    éĹªçĥģ
    -0.08
    åIJ¸åıĸ
    -0.08
    æ¼ıæ´ŀ
    -0.08
    èµ°å¾Ĺ
    -0.08
     GRAT
    -0.08
     bog
    -0.08
    诲
    -0.08
    ç£ĭ
    -0.08
    POSITIVE LOGITS
    人åı£
    0.23
    population
    0.18
     population
    0.17
     наÑģелениÑı
    0.16
    ä¸ĩ人
    0.15
    Population
    0.14
     populations
    0.14
    人群
    0.14
    å±ħæ°ij
    0.14
     Population
    0.14
    Activations Density 0.138%

    No Known Activations