© 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. 55397
    Prev
    Next
    INDEX
    Explanations

    why questions

    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
    å¾ģ
    -0.10
    å¾µ
    -0.10
    è¾ŀ
    -0.09
    ernals
    -0.09
     пÑĢож
    -0.09
    æĢĿ绪
    -0.08
     wanna
    -0.08
    åĬŁåĬ³
    -0.08
     Rescue
    -0.08
    راس
    -0.08
    POSITIVE LOGITS
    æľīåIJįçļĦ
    0.10
    æīĢè°ĵçļĦ
    0.10
     Ful
    0.10
    åĩŃ
    0.10
    究竣æĺ¯
    0.09
    被称为
    0.09
    åįģä½Ļå¹´
    0.09
    åĩŃåĢŁ
    0.08
    íĻĶ
    0.08
    istan
    0.08
    Activations Density 0.030%

    No Known Activations