© 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. 57468
    Prev
    Next
    INDEX
    Explanations

    men / menarche / bankruptcy / anemia

    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
    ÑįÑĤомÑĥ
    -0.12
    ÙĬØ«
    -0.11
    onacci
    -0.09
    IGIN
    -0.09
    ëģĶ
    -0.09
    大è§Ħ模
    -0.09
    ç§ķ
    -0.09
    áĢĸ
    -0.08
    juries
    -0.08
    ç§ijæĬĢ大åѦ
    -0.08
    POSITIVE LOGITS
    pet
    0.08
     Petr
    0.08
    ers
    0.08
    lets
    0.08
    ¬
    0.08
    ãĤĮãģŁ
    0.08
    ific
    0.08
     UPC
    0.08
    åĴ±ä»¬
    0.08
    mgr
    0.08
    Activations Density 0.562%

    No Known Activations