© 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. 61121
    Prev
    Next
    INDEX
    Explanations

    brown bag series or brownouts

    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
    endo
    -0.09
    вол
    -0.09
    æľŁåĨħ
    -0.08
    å«ļ
    -0.08
     Central
    -0.08
    çĬ¹è±«
    -0.08
    åĪ¤å¤Ħ
    -0.08
    pend
    -0.08
    ä½ķãģĭ
    -0.08
    æľ¬å±Ĭ
    -0.08
    POSITIVE LOGITS
    /gr
    0.10
     дела
    0.10
    æ¦Ī
    0.10
    иÑĪ
    0.10
    çĦ¦
    0.09
    åIJĦå¼ı
    0.09
    è¤IJèī²
    0.09
    èī²è°ĥ
    0.09
    ĶåĽŀ
    0.09
    æĮ«
    0.09
    Activations Density 0.019%

    No Known Activations