© 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. 51185
    Prev
    Next
    INDEX
    Explanations

    IT Drivers

    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
     Kah
    -0.08
    known
    -0.08
    KNOWN
    -0.08
    æī§
    -0.08
    ene
    -0.08
     dead
    -0.08
     known
    -0.08
    å¤ı天
    -0.08
    limited
    -0.08
    itung
    -0.08
    POSITIVE LOGITS
    æ²»çIJĨ
    0.11
    éĸĴ
    0.10
    éĹ²
    0.10
    æ²»çIJĨä½ĵç³»
    0.09
    _usage
    0.09
     FA
    0.09
    è¾ĩ
    0.09
     اÙĦداخÙĦ
    0.09
    综åIJĪæ²»çIJĨ
    0.09
    ROI
    0.09
    Activations Density 0.076%

    No Known Activations