© 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. 32353
    Prev
    Next
    INDEX
    Explanations

    fog

    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
    æĦıä¹īä¸ĬçļĦ
    -0.10
    oop
    -0.09
     Manson
    -0.08
    褰
    -0.08
    é£İè²Į
    -0.08
    æ½ľ
    -0.08
    éĴ¾
    -0.08
    MASK
    -0.08
     ê²
    -0.08
    anything
    -0.08
    POSITIVE LOGITS
    gage
    0.10
    ging
    0.10
    иÑĢÑĥ
    0.09
    landers
    0.09
    liner
    0.09
    rends
    0.09
    ranges
    0.09
    lining
    0.09
    ï¸ı
    0.08
    tier
    0.08
    Activations Density 0.004%

    No Known Activations