© 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. 35470
    Prev
    Next
    INDEX
    Explanations

    Bolt, Borg, Stream, map, dd

    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
    祸
    -0.11
    бой
    -0.09
    æķĻèĤ²æķĻåѦ
    -0.09
    _bases
    -0.09
    _effects
    -0.09
     grease
    -0.09
    omes
    -0.09
    æĪIJç«ĭäºĨ
    -0.09
    antry
    -0.09
    ðŁı»
    -0.09
    POSITIVE LOGITS
    æľ¨èĢ³
    0.10
    以åīį
    0.09
    æĶ¯éħį
    0.09
    å½ĵä»ĸ
    0.08
    spo
    0.08
    æĪijè¿ĺæĺ¯
    0.08
    ieve
    0.08
    涧
    0.08
    ä¸ĩç§ij
    0.08
    æŀ·
    0.08
    Activations Density 0.008%

    No Known Activations