© 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. 6426
    Prev
    Next
    INDEX
    Explanations

    adverbs describing 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
    esser
    -0.10
     ÑĤакого
    -0.10
    untime
    -0.10
    忸
    -0.10
    ä½łå¥½
    -0.09
    çī¹åĪ«
    -0.09
    说å¾Ĺ
    -0.09
    ÑģÑĤавка
    -0.09
    æĻĤåĢĻ
    -0.09
    é¨
    -0.09
    POSITIVE LOGITS
    èݽ
    0.09
    ä¸į失
    0.09
    ä¸įæĸŃåľ°
    0.09
    åĨĻçĿĢ
    0.09
    able
    0.09
    elon
    0.08
    ographically
    0.08
     conc
    0.08
    3
    0.08
    2
    0.08
    Activations Density 0.120%

    No Known Activations