© 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. 57584
    Prev
    Next
    INDEX
    Explanations

    by applicable

    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
    annis
    -0.10
    rian
    -0.09
    iterated
    -0.09
    è¿ĺæĥ³
    -0.09
    æ»ļ
    -0.09
    oria
    -0.08
     ÑĢаÑģ
    -0.08
    åĤij
    -0.08
    è¿Ļ个è¡Įä¸ļ
    -0.08
    _REFERENCE
    -0.08
    POSITIVE LOGITS
    çĶŁåij½çļĦ
    0.11
    æłĩæĺİ
    0.09
    å¿ħè¦ģçļĦ
    0.09
    éĢ¼
    0.08
    éĤ£æł·
    0.08
    Abr
    0.08
    å®ĺåı¸
    0.08
    ä¸įåı¯éģ¿åħį
    0.08
     Maher
    0.08
    zym
    0.08
    Activations Density 0.030%

    No Known Activations