© 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. 48460
    Prev
    Next
    INDEX
    Explanations

    ban or limit actions

    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
    IDES
    -0.09
    ATTER
    -0.09
    ван
    -0.09
    ÑĮе
    -0.09
    deer
    -0.09
    éĩİ
    -0.09
    çİ°åŃĺ
    -0.09
    æIJ¬å®¶
    -0.09
    享åıĹåĪ°
    -0.09
    кÑĥÑĢ
    -0.09
    POSITIVE LOGITS
    2
    0.09
    3
    0.09
    è°ĥçłĶ
    0.08
    妥
    0.08
    4
    0.08
    éĴĵé±¼
    0.08
    æ£ĢéªĮ
    0.08
    çĦī
    0.08
    5
    0.08
    论æĸĩ
    0.07
    Activations Density 0.057%

    No Known Activations