© 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. 10603
    Prev
    Next
    INDEX
    Explanations

    Spike, Harry, him, her, she, he

    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
    èĢĻ
    -0.10
    å¹¢
    -0.10
    éķ¿éķ¿
    -0.09
    缴è¨Ģ
    -0.09
    æĵį
    -0.09
    orio
    -0.09
    ServiceProvider
    -0.09
    涸
    -0.08
    owell
    -0.08
    alar
    -0.08
    POSITIVE LOGITS
    /her
    0.10
    对äºİæĪij们
    0.09
    åħ³äºİæĪij们
    0.09
    ä»Ĭå¹´
    0.09
    å¦ĤæľŁ
    0.09
    ennis
    0.08
    对æĪij们
    0.08
    _Pin
    0.08
     Peek
    0.08
    æĹłè®º
    0.08
    Activations Density 0.038%

    No Known Activations