© 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. 58745
    Prev
    Next
    INDEX
    Explanations

    freedom to, freedom of

    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
    åıįå°Ħ
    -0.11
    身æĿIJ
    -0.10
    åIJ¬åIJ¬
    -0.10
    åıįæĢĿ
    -0.09
    åĴĦ
    -0.09
    åĶı
    -0.09
    鼶ç¢İ
    -0.09
    nect
    -0.09
    pson
    -0.09
    ewn
    -0.09
    POSITIVE LOGITS
    èĩªåľ¨
    0.18
    èĩªçĶ±
    0.15
     freedom
    0.13
    Freedom
    0.12
     khá»ıi
    0.11
     ìŀIJìľł
    0.11
     Ñģвобод
    0.10
    ë¡Ń
    0.10
     Ñģвоб
    0.10
    -floating
    0.10
    Activations Density 0.029%

    No Known Activations