© 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. 30574
    Prev
    Next
    INDEX
    Explanations

    plaque detection and characterization

    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
    æݾ
    -0.10
    æľĽ
    -0.10
    éİ®
    -0.09
    æ²¾
    -0.09
     Mend
    -0.09
    è¿ĽæĿ¥
    -0.08
    é£İåIJ¹
    -0.08
     accommodating
    -0.08
    ulp
    -0.08
    etr
    -0.08
    POSITIVE LOGITS
    åŀ¢
    0.10
    çĹĤ
    0.10
    åŀĥåľ¾
    0.10
    çµ®
    0.10
    çĹ°
    0.10
    çĻ½çĻ½
    0.10
    å±ij
    0.10
    åĺĺ
    0.09
    avia
    0.09
     Spurs
    0.09
    Activations Density 0.135%

    No Known Activations