© 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. 9979
    Prev
    Next
    INDEX
    Explanations

    features and compatibility

    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
    èĩ´åĬĽ
    -0.10
    ÌĢ
    -0.10
    amon
    -0.10
    eton
    -0.10
    åŃij
    -0.09
    èĩ´åĬĽäºİ
    -0.09
    ä¸įæĪIJ
    -0.09
    åħ¨éĿ¢èIJ½å®ŀ
    -0.09
    _MAG
    -0.09
    ä¸Ģå¹ħ
    -0.09
    POSITIVE LOGITS
    anguages
    0.09
    éªĬ
    0.09
    urn
    0.08
    俪
    0.08
    å¤ļç§į
    0.08
    TURE
    0.08
    èĻŀ
    0.08
    ihil
    0.08
     ‘
    0.08
    è°ģçŁ¥éģĵ
    0.08
    Activations Density 0.073%

    No Known Activations