© 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. 31915
    Prev
    Next
    INDEX
    Explanations

    posterior cerebral artery

    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
     Recorded
    -0.09
    æIJŀ好
    -0.09
    esteem
    -0.09
    elage
    -0.09
    .isSuccess
    -0.09
    æ·
    -0.08
    eral
    -0.08
    æĩĤäºĭ
    -0.08
    æ»Ķ
    -0.08
    æ¹
    -0.08
    POSITIVE LOGITS
     clue
    0.13
    线索
    0.13
     clues
    0.10
    è°ľ
    0.10
    alen
    0.10
    éĿ¢åŃĶ
    0.10
    åIJĦè¡Į
    0.10
     Ñģлова
    0.09
     crossword
    0.09
    TES
    0.09
    Activations Density 0.025%

    No Known Activations