© 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. 30163
    Prev
    Next
    INDEX
    Explanations

    foundation, Found, foundational

    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
    assel
    -0.09
    enna
    -0.09
    oj
    -0.09
    REW
    -0.08
    çĨŁæĤīçļĦ
    -0.08
    éĢļä¿Ĺ
    -0.08
    çIJ°
    -0.08
    addock
    -0.08
     détail
    -0.08
    人æ°Ķ
    -0.08
    POSITIVE LOGITS
    /Foundation
    0.13
    åŁºçŁ³
    0.11
     foundation
    0.11
    åŁºç¡Ģ
    0.11
     foundations
    0.10
    ç¡Ģ
    0.10
    åĿļå®ŀ
    0.10
    ç¢ĩ
    0.10
    夯å®ŀ
    0.09
    ç®ĹäºĨ
    0.09
    Activations Density 0.045%

    No Known Activations