© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51318
    Prev
    Next
    INDEX
    Explanations

    information below

    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
    åľ¨è¿ĻéĩĮ
    -0.10
    为ä¹ĭ
    -0.09
    ä»Ģä¹Īä¸ľè¥¿
    -0.09
    è¿ĻæŶåĢĻ
    -0.09
    UED
    -0.08
    éĿ¢ä¸´çĿĢ
    -0.08
    è°´
    -0.08
    aly
    -0.08
    è¿Ļè¾¹
    -0.08
    以åīį
    -0.08
    POSITIVE LOGITS
    æ¡Ĩ
    0.11
    ä»Ĩ
    0.10
    æľŁå¾ħ
    0.09
    éŃĶ鬼
    0.09
    ðŁijĩ
    0.09
    ç®Ń
    0.08
    çĨł
    0.08
    ä¸ĭæĸ¹
    0.08
    åŃĹæł·
    0.08
    avec
    0.08
    Activations Density 0.218%

    No Known Activations