© 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. 11804
    Prev
    Next
    INDEX
    Explanations

    executable files (.exe)

    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
    ãģ¤ãĤĤãĤĬ
    -0.10
    инÑĭ
    -0.09
    untime
    -0.09
    oins
    -0.09
     Ñĥзна
    -0.09
    ä¸Ŀ绸ä¹ĭè·¯
    -0.09
    аÑħ
    -0.09
    ãĥªãĥ³ãĤ°
    -0.09
    ëŀij
    -0.09
    oret
    -0.09
    POSITIVE LOGITS
    olini
    0.09
    æѤåĪ»
    0.09
    omo
    0.08
     moto
    0.08
    à¹Ĥà¸ģ
    0.08
    .quiz
    0.08
    ecs
    0.08
    lix
    0.08
     Milo
    0.08
    缤
    0.07
    Activations Density 0.193%

    No Known Activations