© 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. 10205
    Prev
    Next
    INDEX
    Explanations

    fairy ring, soil, compost

    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
    æĻļé¥Ń
    -0.10
    æ³Ľ
    -0.10
    è¿ĻæĶ¯
    -0.09
    ä¸ŃåĽ½å¤§éĻĨ
    -0.08
    ä½İåİĭ
    -0.08
    adic
    -0.08
    æĻĮ
    -0.08
    åѤ
    -0.08
    æĻļéĹ´
    -0.08
    éĽ¹
    -0.08
    POSITIVE LOGITS
    èĢķåľ°
    0.11
    åľŁå£¤
    0.11
     compost
    0.10
    åĪ¨
    0.10
    terra
    0.10
    棱
    0.10
    æĶ¹èī¯
    0.09
     raised
    0.09
     Raised
    0.09
    æĪĺ
    0.09
    Activations Density 0.107%

    No Known Activations