© 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. 36443
    Prev
    Next
    INDEX
    Explanations

    check out

    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
    rement
    -0.10
    ault
    -0.09
    kip
    -0.09
    å§ĭç»Īä¿ĿæĮģ
    -0.09
    avig
    -0.08
    ģ
    -0.08
    imuth
    -0.08
    è¾ij
    -0.08
    æģIJæħĮ
    -0.08
    ä¿IJ
    -0.08
    POSITIVE LOGITS
    两类
    0.10
    æĪijçľĭ
    0.09
    otron
    0.09
    æĪijè¿ĺæĺ¯
    0.09
    åĴĮåľ°åĮº
    0.09
    éĽ¾
    0.09
     unf
    0.08
    åİī
    0.08
    leo
    0.08
    æıIJ
    0.08
    Activations Density 0.006%

    No Known Activations