© 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. 37927
    Prev
    Next
    INDEX
    Explanations

    life transitions and job history

    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
    裹
    -0.09
    åĬłæ·±
    -0.09
    对çĿĢ
    -0.09
     Scope
    -0.09
    aris
    -0.08
    æķ´ä¸ª
    -0.08
    éĿł
    -0.08
    åĪĴå®ļ
    -0.08
    Repair
    -0.08
    è¿ĩåħ³
    -0.08
    POSITIVE LOGITS
    è¾Ĺ转
    0.11
    å¤ļ彩
    0.10
     destinations
    0.10
    å¾ĹæĦı
    0.09
    çļĦæľĢåIJİä¸Ģ
    0.09
    çļĦåij½è¿IJ
    0.09
    åij¨è½¬
    0.09
    \Eloquent
    0.09
    åľ¨åĵªéĩĮ
    0.09
    代价
    0.09
    Activations Density 0.192%

    No Known Activations