© 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. 23597
    Prev
    Next
    INDEX
    Explanations

    asking wh- questions

    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
    ide
    -0.08
    æĻŁ
    -0.08
     excursion
    -0.07
    2
    -0.07
     pau
    -0.07
    éĤ¦
    -0.07
    .variables
    -0.07
    æŀĿ
    -0.07
     vid
    -0.07
    8
    -0.07
    POSITIVE LOGITS
    å¦Ĥä½ķ
    0.13
    为åķ¥
    0.13
    ä½łæĢİä¹Ī
    0.13
    为ä»Ģä¹Īä¸į
    0.13
    æĺ¯å¦Ĥä½ķ
    0.13
    å¦Ĥä½ķçľĭå¾ħ
    0.13
    å¦Ĥä½ķåİ»
    0.13
    为ä»Ģä¹Ī
    0.12
    æĺ¯æĢİæł·
    0.12
     how
    0.12
    Activations Density 0.112%

    No Known Activations