© 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. 11067
    Prev
    Next
    INDEX
    Explanations

    television contexts

    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
    çĪ¹
    -0.10
    ÑģÑĤÑĢой
    -0.10
     ebook
    -0.10
    isd
    -0.10
    à²Ł
    -0.09
    æ¼Ĩ
    -0.09
    çĹ
    -0.09
    颦
    -0.09
    æīĭæľº
    -0.08
    odiac
    -0.08
    POSITIVE LOGITS
    ðŁĵº
    0.09
    çŀ¬
    0.09
    oons
    0.09
    -TV
    0.09
    渺
    0.08
    çī¹æĸ¯
    0.08
    éħį
    0.08
     ifs
    0.08
    зÑĭ
    0.08
    èĢģå®ŀ
    0.08
    Activations Density 0.066%

    No Known Activations