© 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. 50981
    Prev
    Next
    INDEX
    Explanations

    something or anything

    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
    è¿Ļ两ç§į
    -0.10
     пÑĢид
    -0.09
    éķ¿è¾¾
    -0.09
    åĪļ
    -0.09
    è¿Łè¿Ł
    -0.09
    æīĭä¸Ń
    -0.08
    åľ¨åĨħçļĦ
    -0.08
     yüksel
    -0.08
    åIJįåŃĹ
    -0.08
    åĴ¬
    -0.08
    POSITIVE LOGITS
    äºĽä»Ģä¹Ī
    0.22
     something
    0.21
    something
    0.20
    ä»Ģä¹Īä¸ľè¥¿
    0.18
     anything
    0.18
    ä½ķãģĭ
    0.18
    ä»Ģä¹Ī
    0.17
     nothing
    0.17
    Something
    0.16
    à¸Ńะà¹Ħร
    0.16
    Activations Density 0.177%

    No Known Activations