© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37591
    Prev
    Next
    INDEX
    Explanations

    same

    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
    æĤī
    -0.11
    æīĢéľĢè¦ģ
    -0.10
    ogl
    -0.10
    æīĢéľĢçļĦ
    -0.09
    è¿ĩåĪĨ
    -0.09
     Weeks
    -0.09
    椿
    -0.09
    箫
    -0.09
    uhe
    -0.09
    æīĢéľĢè¦ģçļĦ
    -0.09
    POSITIVE LOGITS
    æ¹Ħ
    0.09
    atta
    0.09
     same
    0.09
    ä¹Łå¥½
    0.09
    еÑģÑĤÑĮ
    0.08
    EP
    0.08
    .lv
    0.08
    $$$
    0.08
     shot
    0.08
    èİİ
    0.08
    Activations Density 0.242%

    No Known Activations