© 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. 27884
    Prev
    Next
    INDEX
    Explanations

    OK button on alerts

    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
    Ä°LÄ°
    -0.09
    æ¹ĸåĮº
    -0.09
     permalink
    -0.09
     Seks
    -0.08
    åĬŁè¯¾
    -0.08
    éĥ¨ç½²
    -0.08
    ç§Ģ丽
    -0.08
    ãĥģãĥ¥
    -0.08
    Fallback
    -0.08
    èĺ¸
    -0.08
    POSITIVE LOGITS
    继ç»Ń
    0.11
     OK
    0.10
     yes
    0.10
    OK
    0.10
     proceeding
    0.10
    Yes
    0.10
    odal
    0.10
    _YES
    0.10
     Yes
    0.10
     Continue
    0.10
    Activations Density 0.130%

    No Known Activations