© 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. 17436
    Prev
    Next
    INDEX
    Explanations

    acronyms or word endings like -ac, -ad, -ar, -ace

    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
    èĤ©
    -0.09
    åĸľæ¬¢
    -0.09
    èIJ½å®ŀ
    -0.09
    inesis
    -0.09
    迸
    -0.09
    æī¿
    -0.09
    lock
    -0.09
    æīĵæĬĺ
    -0.08
    éķķ
    -0.08
    craft
    -0.08
    POSITIVE LOGITS
     acronym
    0.10
    atron
    0.09
    æĿµ
    0.09
    usercontent
    0.09
    yne
    0.08
    acen
    0.08
    éĵ¤
    0.08
    .condition
    0.07
    çļĦéģĵçIJĨ
    0.07
    çĪª
    0.07
    Activations Density 0.174%

    No Known Activations