© 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. 26820
    Prev
    Next
    INDEX
    Explanations

    starting to grow

    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
    ä¾ĥ
    -0.11
    é¦Ĭ
    -0.10
    æ³īæ°´
    -0.10
    é»İæĺİ
    -0.10
    çģ«èĬ±
    -0.10
    çIJĨå·¥
    -0.09
    çĥŃè¡Ģ
    -0.09
    èij¬
    -0.09
    ç»ıåķĨ
    -0.08
    erton
    -0.08
    POSITIVE LOGITS
    çĶŁéķ¿
    0.18
     growth
    0.12
    æĪIJéķ¿
    0.11
    å¢ŀéķ¿
    0.11
    å¾Ĵ
    0.10
    growth
    0.10
    èĮİ
    0.10
    è¿Ļä¸Ģå¹´
    0.10
    ç¹ģæ®ĸ
    0.10
    rowth
    0.10
    Activations Density 0.052%

    No Known Activations