© 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. 56303
    Prev
    Next
    INDEX
    Explanations

    honor or tribute to

    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
    åįĸæİī
    -0.09
    front
    -0.09
    osl
    -0.09
    scoped
    -0.08
    çķ¥
    -0.08
    éħĭ
    -0.08
    laden
    -0.08
    ä¸Ĭç½ij
    -0.08
    缤
    -0.08
    ers
    -0.08
    POSITIVE LOGITS
    éĢĿ
    0.11
    è¿ĩåİ»çļĦ
    0.11
    ä¼Łå¤§çļĦ
    0.10
    éĤ£äºĽ
    0.10
    دا
    0.09
    æĹĥ
    0.09
    èĸ®
    0.09
    èĢĺ
    0.09
    è¿ĩåİ»
    0.08
    çī¹å®ļ
    0.08
    Activations Density 0.035%

    No Known Activations