© 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. 52101
    Prev
    Next
    INDEX
    Explanations

    time for

    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
    erus
    -0.10
    交éĻħ
    -0.10
    åħ¶æīĢ
    -0.09
    èĤ´
    -0.09
    社ä¼ļ主ä¹ī
    -0.09
    acia
    -0.09
    èĽĽ
    -0.08
    _perms
    -0.08
    eday
    -0.08
    æľªæĪIJ
    -0.08
    POSITIVE LOGITS
    æĥ³åĬŀæ³ķ
    0.09
    é«ĺ度
    0.09
    åıijæĮ¥ä½ľçĶ¨
    0.09
    stants
    0.09
    arro
    0.08
    Avoid
    0.08
    ç¿ĺ
    0.08
    coder
    0.08
    usiness
    0.08
    tw
    0.08
    Activations Density 0.021%

    No Known Activations