© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52821
    Prev
    Next
    INDEX
    Explanations

    the + noun

    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
    ãģĬ
    -0.16
    ãģĻãģIJãģ«
    -0.13
    ãģĤãģ¾ãĤĬ
    -0.12
    ãģĤãģ£ãģŁ
    -0.12
    ãĤĤãģ®
    -0.11
    ãģĤãģ£ãģ¦
    -0.11
    人éĥ½
    -0.11
    ãģĻãģ§ãģ«
    -0.11
    ãģĻãģIJ
    -0.10
    ãģĬåĭ§ãĤģ
    -0.10
    POSITIVE LOGITS
     sake
    0.21
     purposes
    0.16
    bidden
    0.15
    geries
    0.14
    -profit
    0.13
    æĸ°çļĦä¸Ģå¹´
    0.12
    amt
    0.12
    chten
    0.11
    cht
    0.11
    ä¹łæĥ¯äºĨ
    0.10
    Activations Density 0.118%

    No Known Activations