© 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. 49897
    Prev
    Next
    INDEX
    Explanations

    rag-tag

    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
    ksen
    -0.11
    à¹Į
    -0.10
    ÑģÑı
    -0.09
    ally
    -0.09
    åīįæľŁ
    -0.09
    ÙħÙĬÙĨ
    -0.09
    gaard
    -0.08
    ç¢ij
    -0.08
    æ½ĩæ´Ĵ
    -0.08
    rops
    -0.08
    POSITIVE LOGITS
    ulous
    0.09
    doll
    0.09
    овÑĭй
    0.09
     gì
    0.09
     Ñģобой
    0.09
    æ¶İ
    0.09
    ged
    0.09
    å±Ĥ次
    0.08
     rag
    0.08
    ги
    0.08
    Activations Density 0.009%

    No Known Activations