© 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. 33046
    Prev
    Next
    INDEX
    Explanations

    freedom, choice, and agency

    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
    RIES
    -0.10
    åı¯è§Ĩ
    -0.09
    unar
    -0.09
    åĽº
    -0.09
    -mf
    -0.08
    æĤĦ
    -0.08
    ãģ¡
    -0.08
    æĬĺ
    -0.08
    rä
    -0.08
    æĥ³å¿µ
    -0.08
    POSITIVE LOGITS
    åĤĢ
    0.10
     Hav
    0.10
    æĸ¹åIJijçĽĺ
    0.09
    仨
    0.09
     Ñģвоб
    0.09
    æłĹ
    0.09
    èĩªä¸»
    0.09
    _agents
    0.09
     human
    0.09
     liberty
    0.09
    Activations Density 0.036%

    No Known Activations