© 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. 30690
    Prev
    Next
    INDEX
    Explanations

    testing and code planning

    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
    .testing
    -0.09
    çĭŀ
    -0.09
     inputValue
    -0.08
    éĿ³
    -0.08
    寡
    -0.08
    sher
    -0.08
    è¤IJ
    -0.08
     пÑĢÑı
    -0.08
    ç»Ļä»ĸ
    -0.08
     напÑĢавлен
    -0.08
    POSITIVE LOGITS
    éĻĤ
    0.11
    spo
    0.10
    åijĬåĪ«
    0.10
    åįļ
    0.10
    ä¹ħ
    0.09
    åĤ¨å¤ĩ
    0.09
    æŃ¥è¡Į
    0.09
    æĸ©
    0.09
    strt
    0.09
     Spo
    0.09
    Activations Density 0.273%

    No Known Activations