© 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. 18771
    Prev
    Next
    INDEX
    Explanations

    so followed by can, far, many, do, did, much, has, too

    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
    èĥŃ
    -0.09
    uations
    -0.09
    ï¸ı
    -0.09
    è¯ĺ
    -0.09
    æĪij们å¿ħé¡»
    -0.09
    otas
    -0.09
    anus
    -0.08
    åı£ä¸Ń
    -0.08
    çĩĥ
    -0.08
    æ³Ĭ
    -0.08
    POSITIVE LOGITS
    umont
    0.09
    人çļĦ
    0.08
     Trev
    0.08
    ieri
    0.08
    人éĥ½
    0.08
     happens
    0.08
    ä¸ĩåIJį
    0.08
    lard
    0.08
    å¥ĸ
    0.08
     happened
    0.08
    Activations Density 0.007%

    No Known Activations