© 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. 48719
    Prev
    Next
    INDEX
    Explanations

    Executive Committee or Order

    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
    æĺ¶
    -0.10
    çŃī级
    -0.09
    æİĩ
    -0.09
    è°ı
    -0.09
    åīįæıIJ
    -0.08
    èİ«
    -0.08
    嵩
    -0.08
    vana
    -0.08
    ¹Ħ
    -0.08
    åı¦
    -0.08
    POSITIVE LOGITS
    ISTR
    0.10
    fä
    0.09
    oui
    0.09
    æIJĸ
    0.09
    ÐĽÐŀ
    0.09
    ETY
    0.09
    UGE
    0.09
    LOY
    0.09
    æijĩäºĨ
    0.09
    æĨij
    0.09
    Activations Density 0.011%

    No Known Activations