© 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. 7487
    Prev
    Next
    INDEX
    Explanations

    regulation and control

    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
    omal
    -0.10
    è¿Ŀè§Ħ
    -0.09
    ches
    -0.09
    -Russian
    -0.09
    è§Ħå¾ĭ
    -0.08
    à¸Ĥาว
    -0.08
    èįIJ
    -0.08
    ndl
    -0.08
    ritic
    -0.08
    æĨİ
    -0.08
    POSITIVE LOGITS
    æѤäºĭ
    0.10
    ur
    0.09
    egin
    0.09
    vere
    0.09
    gable
    0.09
     اÙĦØ£Ùħر
    0.09
    ear
    0.09
    ester
    0.08
    æĦıä¹īä¸ĬçļĦ
    0.08
    ourke
    0.08
    Activations Density 0.045%

    No Known Activations