© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18139
    Prev
    Next
    INDEX
    Explanations

    licensed, registered, authorized, qualified

    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
    æĹ©æĻ¨
    -0.10
    è¾ħ导åijĺ
    -0.10
    _interfaces
    -0.09
    ä¸įä¸ĭ
    -0.09
    æĬ¢
    -0.09
    ause
    -0.09
    eldon
    -0.09
    å¸ĥæĭī
    -0.09
    имеÑĢ
    -0.09
    inez
    -0.09
    POSITIVE LOGITS
    èµĦè´¨
    0.09
    æĦŁæŁĵèĢħ
    0.08
    gün
    0.08
    èĩªè§ī
    0.08
     registered
    0.08
    оваÑĢ
    0.08
    obi
    0.08
     independent
    0.08
     Pere
    0.08
    cele
    0.08
    Activations Density 0.108%

    No Known Activations