© 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. 61424
    Prev
    Next
    INDEX
    Explanations

    LANGUAGE Declarations

    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
    åĽº
    -0.10
    Rh
    -0.09
     Rh
    -0.09
     возможноÑģÑĤи
    -0.09
    æºĺ
    -0.09
    _TestCase
    -0.08
    è°
    -0.08
    åĢ¡
    -0.08
    éģĦ
    -0.08
    hole
    -0.08
    POSITIVE LOGITS
    çģŃ
    0.10
    æ»ħ
    0.10
    éħĴä¸ļ
    0.10
    iry
    0.09
     tert
    0.09
    çĥģ
    0.09
    èĤĿèĦı
    0.09
    åĴĨ
    0.09
    积æ·Ģ
    0.08
    çĹĤ
    0.08
    Activations Density 0.052%

    No Known Activations