© 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. 30827
    Prev
    Next
    INDEX
    Explanations

    therapy sessions and lessons

    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
    éĩįè§Ĩ
    -0.10
    è¿Ķ
    -0.09
     Sy
    -0.08
    agens
    -0.08
    hamster
    -0.08
    è¾Ľ
    -0.08
    é¦ĸåıij
    -0.08
    åı
    -0.08
     incom
    -0.08
    ivre
    -0.08
    POSITIVE LOGITS
     sessions
    0.11
    è¾ħ导
    0.11
     session
    0.10
    Sessions
    0.09
    åĢı
    0.09
    (compact
    0.09
    Session
    0.09
    æĸ«
    0.09
     Sessions
    0.09
    æ¡Ģ
    0.09
    Activations Density 0.088%

    No Known Activations