© 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. 36963
    Prev
    Next
    INDEX
    Explanations

    corner

    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
    orch
    -0.09
    æīĭæĮĩ
    -0.09
     açıkl
    -0.08
    ä¼IJ
    -0.08
    饮çĶ¨æ°´
    -0.08
    粤
    -0.08
    icc
    -0.08
    /pm
    -0.08
    使çĶ¨çļĦ
    -0.08
    åĬ©
    -0.08
    POSITIVE LOGITS
     corner
    0.19
    corner
    0.18
     Corner
    0.18
     corners
    0.16
    Corner
    0.16
    è§ĴèIJ½
    0.16
    -corner
    0.15
    _corner
    0.15
    è§Ĵ
    0.14
    ä¸Ģè§Ĵ
    0.11
    Activations Density 0.043%

    No Known Activations