© 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. 17651
    Prev
    Next
    INDEX
    Explanations

    freedom and liberty rights

    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
    伤
    -0.10
    æĺĩ
    -0.10
    å¿ĥ头
    -0.09
    ams
    -0.08
     Andres
    -0.08
    iment
    -0.08
    LEM
    -0.08
    ç½®
    -0.08
    å¿ĥåºķ
    -0.08
    è´Ŀ壳
    -0.08
    POSITIVE LOGITS
    åĮĸè¿Ľç¨ĭ
    0.10
    меÑģ
    0.09
     freedoms
    0.09
    OfWork
    0.09
    ossip
    0.08
    ä¹ĸä¹ĸ
    0.08
    被æįķ
    0.08
    unker
    0.08
    åı¯æĥ³èĢĮ
    0.08
    uft
    0.08
    Activations Density 0.009%

    No Known Activations