© 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. 30661
    Prev
    Next
    INDEX
    Explanations

    exempt, immunity, officially neutral

    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
    èĢį
    -0.12
    èĬİ
    -0.10
    ÂŃi
    -0.10
     Destiny
    -0.09
    éĢı
    -0.09
    å¥ĸåѦéĩij
    -0.09
    女æĢ§
    -0.08
    dez
    -0.08
    wnd
    -0.08
    urgeon
    -0.08
    POSITIVE LOGITS
    è±ģ
    0.11
    åħįè´£
    0.11
    åħį
    0.09
    åħįéĻ¤
    0.09
     exempt
    0.09
    åħ¬åĬ¡
    0.09
    åħįç¨İ
    0.09
     immunity
    0.09
    ä¸ĵ享
    0.09
    æĶĺ
    0.09
    Activations Density 0.078%

    No Known Activations