© 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. 1072
    Prev
    Next
    INDEX
    Explanations

    years old

    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
    Ñģлож
    -0.09
    æĸ°åĮº
    -0.09
    æĪIJè´¥
    -0.09
    æ½ŀ
    -0.09
    ä¹İ
    -0.09
    æİĴ污
    -0.09
    åįĩ温
    -0.08
    unch
    -0.08
    å·²ä¹ħçļĦ
    -0.08
    flix
    -0.08
    POSITIVE LOGITS
    ä¸įä¸ĭ
    0.09
    shal
    0.08
    ì§ľ
    0.08
    åīįæīĢ
    0.07
     Sham
    0.07
     Trot
    0.07
    _erase
    0.07
    管å±Ģ
    0.07
     lastIndex
    0.07
    èĥ¤
    0.07
    Activations Density 0.023%

    No Known Activations