© 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. 27811
    Prev
    Next
    INDEX
    Explanations

    living room features

    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
    elter
    -0.10
    ople
    -0.09
    帼
    -0.09
    夫
    -0.09
    å¹³éĿĻ
    -0.09
    害
    -0.09
     ÑģеÑĢии
    -0.09
     divor
    -0.09
    移æ¤į
    -0.09
    éĺħåİĨ
    -0.09
    POSITIVE LOGITS
    éĩĮéĿ¢æľī
    0.10
    éĿ¢åħ·
    0.09
     Vul
    0.08
     ÙĪاÙĦع
    0.08
    åĪģ
    0.08
    rome
    0.08
    ä¼´æľī
    0.08
     Accessed
    0.08
    egin
    0.08
    èĥ´
    0.08
    Activations Density 0.031%

    No Known Activations