© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21671
    Prev
    Next
    INDEX
    Explanations

    of this

    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
    zon
    -0.10
    ä»İä¸ļèĢħ
    -0.10
    룩
    -0.10
    产éĩı
    -0.10
    å½Ĵå±ŀ
    -0.09
    éĢĴç»Ļ
    -0.09
    ä¸Ńå¤ĸ
    -0.09
    ç²ij
    -0.08
    çĨĦ
    -0.08
    lob
    -0.08
    POSITIVE LOGITS
    fully
    0.13
    à¹ĥà¸Ļà¸ģาร
    0.11
    ful
    0.11
    itarian
    0.10
     wisely
    0.10
    FUL
    0.10
    æľĢå¤ļçļĦ
    0.10
    cols
    0.10
     discretion
    0.09
    lessly
    0.09
    Activations Density 1.024%

    No Known Activations