© 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. 33441
    Prev
    Next
    INDEX
    Explanations

    in [adjective/adverb]

    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
     Barnes
    -0.08
    eten
    -0.08
    #+
    -0.08
    æ²¹èĦĤ
    -0.08
     DPS
    -0.08
    çģŀ
    -0.08
     Dialogue
    -0.08
    è¾ı
    -0.08
    .LA
    -0.07
    /on
    -0.07
    POSITIVE LOGITS
    æĿĨèıĮ
    0.10
    eron
    0.09
    ç»ĩ
    0.09
    æľīäºĽäºº
    0.09
    å®°
    0.09
     Undo
    0.09
    ä»İä¸Ń
    0.08
    éĨª
    0.08
    aversal
    0.08
    æѤåĪ»
    0.08
    Activations Density 0.135%

    No Known Activations