© 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. 30836
    Prev
    Next
    INDEX
    Explanations

    chromatin structure and accessibility

    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
     mot
    -0.09
    åĩºåİ»
    -0.09
     mens
    -0.09
    è¿IJæ²³
    -0.09
     Sche
    -0.09
    è¬
    -0.09
    ót
    -0.08
    çĿ«
    -0.08
    ä¿IJ
    -0.08
    çļĦ人çĶŁ
    -0.08
    POSITIVE LOGITS
    _accessible
    0.10
    é¢ģ
    0.10
    ç¥Ń
    0.09
    é£İæ°´
    0.08
     Bruins
    0.08
    æĿ¾å¼Ľ
    0.08
    åij¼åºĶ
    0.08
    ä¸į容æĺĵ
    0.08
     mustard
    0.08
    å¥ijæľº
    0.08
    Activations Density 0.333%

    No Known Activations