© 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. 10843
    Prev
    Next
    INDEX
    Explanations

    success or failure

    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
    åī¯
    -0.10
    à¹Ħว
    -0.09
    å¯Ħ
    -0.09
    å¾Ī好
    -0.09
    åѦéĹ®
    -0.08
    æĶ¹èī¯
    -0.08
    æĶ¾å¿ĥ
    -0.08
    chos
    -0.08
    pper
    -0.08
    iot
    -0.08
    POSITIVE LOGITS
    ihu
    0.10
    çŀ½
    0.09
    姥
    0.09
    æ·±åĪ»çļĦ
    0.09
    çīĿ
    0.09
    åºŀ
    0.08
    èݨ
    0.08
    æĤ²
    0.08
    _FRAGMENT
    0.08
    åĨī
    0.08
    Activations Density 0.046%

    No Known Activations