© 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. 58091
    Prev
    Next
    INDEX
    Explanations

    magnitude followed by outcomes

    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
    æµ·éĩı
    -0.10
    æĹłä¸į
    -0.10
    被æįķ
    -0.10
    çĻ¾å®¶
    -0.09
     vind
    -0.09
    ÙĤت
    -0.09
    gua
    -0.09
    ä¸įå°½
    -0.09
    该æĢİä¹Ī
    -0.08
    æŀķ
    -0.08
    POSITIVE LOGITS
    isas
    0.09
     Mahm
    0.09
     деле
    0.08
    shine
    0.08
    çī
    0.07
     اÙĦشر
    0.07
    å¯Ĵ
    0.07
    .Observer
    0.07
     Into
    0.07
    .cond
    0.07
    Activations Density 0.373%

    No Known Activations