© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8008
    Prev
    Next
    INDEX
    Explanations

    camera, view, light, projection

    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
    纹
    -0.09
    éĤĤ
    -0.09
    zer
    -0.08
    笳
    -0.08
    çļĦä»·åĢ¼
    -0.08
    级
    -0.08
    饿
    -0.08
    鬻
    -0.08
    æ¡£æ¡Ī
    -0.08
    äºĮæľŁ
    -0.08
    POSITIVE LOGITS
    ä¸īç»´
    0.14
    è§Ĩè§Ĵ
    0.12
    ç«ĭä½ĵ
    0.11
    .setView
    0.11
    -view
    0.11
     заÑĤ
    0.11
    å®ŀçī©
    0.11
    AZY
    0.10
     viewpoint
    0.10
    isphere
    0.10
    Activations Density 0.174%

    No Known Activations