© 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. 57111
    Prev
    Next
    INDEX
    Explanations

    with and without

    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
    ⽬
    -0.10
    بث
    -0.10
    æĹłäºº
    -0.10
    毫ä¸įçĬ¹è±«
    -0.09
     fortunes
    -0.09
    æĪ´ä¸Ĭ
    -0.09
    acious
    -0.09
    åħ¶å®ĥéĹ®é¢ĺ
    -0.09
    å¼ķæĿ¥
    -0.09
    PBS
    -0.09
    POSITIVE LOGITS
    ered
    0.10
     regard
    0.10
    hta
    0.10
    åIJĪ
    0.09
     access
    0.08
    象
    0.08
    çĿ¬
    0.08
    ogle
    0.08
    theless
    0.08
     regards
    0.08
    Activations Density 0.067%

    No Known Activations