© 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. 58712
    Prev
    Next
    INDEX
    Explanations

    successful completion

    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
    è¶ģçĿĢ
    -0.12
    åħ¬æĬ¥
    -0.10
    (UI
    -0.10
     gent
    -0.09
    å¸ĥæľĹ
    -0.09
    åįł
    -0.09
    åıªä¼ļ
    -0.09
    \xaa
    -0.09
    å¤ĦåĪĨ
    -0.09
    chte
    -0.09
    POSITIVE LOGITS
     certain
    0.10
     Certain
    0.09
    Certain
    0.09
    åĬ³
    0.08
    符åIJĪ
    0.08
     presumably
    0.08
    è¾Ľèĭ¦
    0.08
    IRT
    0.08
    å¨Ħ
    0.08
    æŁIJäºĽ
    0.08
    Activations Density 0.074%

    No Known Activations