© 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. 51604
    Prev
    Next
    INDEX
    Explanations

    bring general/these/to/back/some/great/this/a/you/your

    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
    æ¶ī
    -0.09
    åĪĨéĶĢ
    -0.09
    横
    -0.09
    çļĦå¢ŀéķ¿
    -0.09
    å°İ
    -0.09
    æĬ¤
    -0.09
    æħĿ
    -0.08
    çļĦåºĶçĶ¨
    -0.08
    ids
    -0.08
    åľ¨åĮĹ京
    -0.08
    POSITIVE LOGITS
    平衡
    0.10
    失åĪ©
    0.10
    kich
    0.10
    uez
    0.09
    ä¸Ģ份
    0.09
    Bes
    0.09
     Outer
    0.09
    é¢ĵ
    0.09
    åĪ·
    0.09
    ç¾İæĦŁ
    0.08
    Activations Density 0.028%

    No Known Activations