© 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. 62675
    Prev
    Next
    INDEX
    Explanations

    hugging, hugs, cuddle, embrace

    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
    baugh
    -0.10
    igation
    -0.09
    (CancellationToken
    -0.09
    æľŁæľ«
    -0.08
    iring
    -0.08
     crud
    -0.08
    è´±
    -0.08
    ISR
    -0.08
    รว
    -0.08
     exig
    -0.08
    POSITIVE LOGITS
    asz
    0.10
    tur
    0.10
    ouro
    0.09
    ../
    0.09
    窮
    0.09
    odal
    0.09
    аÑģ
    0.09
    çIJı
    0.09
    æģ¤
    0.09
    Slf
    0.09
    Activations Density 0.007%

    No Known Activations