© 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. 2796
    Prev
    Next
    INDEX
    Explanations

    extension or expansion of time/scope

    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
    注éĶĢ
    -0.10
    ÑįÑĤаж
    -0.10
    çĥĺ
    -0.09
    é«ĺé¢Ŀ
    -0.09
    è¶ĬæĿ¥è¶Ĭå°ij
    -0.09
    ragen
    -0.09
    âŃ
    -0.09
    .setInput
    -0.09
    orial
    -0.09
    麸
    -0.09
    POSITIVE LOGITS
    æī©å¤§
    0.10
    延éķ¿
    0.10
    éré
    0.09
    å®ī举
    0.09
     doubled
    0.09
    å¹ħ度
    0.08
    åĴĮå®ĮåĸĦ
    0.08
    åĭ¤å¥ĭ
    0.08
    容éĩı
    0.08
    æī©å®¹
    0.08
    Activations Density 0.050%

    No Known Activations