© 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. 39542
    Prev
    Next
    INDEX
    Explanations

    help achieve outcomes

    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
    ZN
    -0.11
    æµģåĬ¨æĢ§
    -0.09
    ä¼ļæľī
    -0.09
    åı¯éĿłæĢ§
    -0.08
    å®īåħ¨æĢ§
    -0.08
    rin
    -0.08
    wt
    -0.08
    ãĤĤãģĦãģĦ
    -0.08
    æĸĩåĮĸ建设
    -0.08
     visits
    -0.08
    POSITIVE LOGITS
    oreach
    0.10
    æ¬
    0.09
     Vest
    0.09
    æ¸ħéĨĴ
    0.09
    èįŁ
    0.09
    _SETTINGS
    0.09
    使åħ¶
    0.09
    Constructed
    0.09
    urma
    0.09
    Locker
    0.08
    Activations Density 0.032%

    No Known Activations