© 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. 7563
    Prev
    Next
    INDEX
    Explanations

    court cases citations

    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
    è¿Ķ
    -0.10
    广çĶµ
    -0.10
    ä¸Ĭå®ĺ
    -0.09
    ç®į
    -0.09
    Datum
    -0.09
    ECTOR
    -0.09
    iat
    -0.09
    ä¸ĭå·´
    -0.09
    ief
    -0.09
    ocks
    -0.09
    POSITIVE LOGITS
    gers
    0.09
    etails
    0.09
     Lis
    0.09
    rist
    0.09
    layan
    0.09
    ame
    0.08
     Vill
    0.08
    ì¦Ŀ
    0.08
    eenth
    0.08
     Polo
    0.08
    Activations Density 0.201%

    No Known Activations