© 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. 32983
    Prev
    Next
    INDEX
    Explanations

    US dollars or currency values

    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
    éĻIJ度
    -0.10
    otic
    -0.09
    bies
    -0.08
    å¤ļ彩
    -0.08
    umm
    -0.08
    éĴ³
    -0.08
    ئ
    -0.08
    çĶŁæ´»ä¹łæĥ¯
    -0.08
    æ²¼
    -0.08
    urring
    -0.08
    POSITIVE LOGITS
    볨
    0.10
    ä¸Ģç¯ĩ
    0.09
    apl
    0.09
    ä¸īåĽĽ
    0.08
    ä¸ĥåħ«
    0.08
    .backends
    0.08
    èıĬ
    0.08
    CreateInfo
    0.08
     Crest
    0.08
    nn
    0.08
    Activations Density 0.009%

    No Known Activations