© 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. 49612
    Prev
    Next
    INDEX
    Explanations

    usr/bin

    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
    afa
    -0.09
    resse
    -0.09
    ä»Ģä¹Īåı«
    -0.08
    HeaderValue
    -0.08
    æĪ³
    -0.08
    ijk
    -0.08
    볬
    -0.08
    ä¼ļå½±åĵįåĪ°
    -0.08
    allah
    -0.08
    éª
    -0.08
    POSITIVE LOGITS
     Garr
    0.09
    æŃ¥è¡Į
    0.09
    nels
    0.09
     Dav
    0.09
    ç²¾
    0.09
    ðŁĻĭ
    0.09
    ë´Ħ
    0.08
    .lu
    0.08
     calor
    0.08
    (named
    0.08
    Activations Density 0.060%

    No Known Activations