© 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. 22284
    Prev
    Next
    INDEX
    Explanations

    genesis | jacob | berlin | tumors | business

    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
    å¼ķæĿ¥
    -0.11
    .choices
    -0.10
    è¿ľå¤Ħ
    -0.10
    è¿ľæĸ¹
    -0.10
    _STRUCTURE
    -0.10
    ç´¯äºĨ
    -0.09
     Yaz
    -0.09
    èĬ±çĵ£
    -0.09
    èł¹
    -0.09
    ä¸Ĭ线
    -0.09
    POSITIVE LOGITS
    å¤ı
    0.09
    opsy
    0.09
     Wrest
    0.09
     vign
    0.08
     lab
    0.08
     Lab
    0.08
     lin
    0.08
     Abraham
    0.08
    ernel
    0.08
     Stamford
    0.08
    Activations Density 0.035%

    No Known Activations