© 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. 31611
    Prev
    Next
    INDEX
    Explanations

    video games, RPGs

    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
    楸
    -0.10
    crest
    -0.10
    æģŃ
    -0.10
    .sid
    -0.08
    强壮
    -0.08
    Structured
    -0.08
    åĬŀ
    -0.08
    redo
    -0.08
    roke
    -0.08
    oku
    -0.08
    POSITIVE LOGITS
    æĦļ
    0.10
    ä¼Ĺ
    0.10
    æŀ¢çº½
    0.09
    füg
    0.09
    åī¥
    0.09
    éĴį
    0.09
    ursive
    0.08
    åĤ»
    0.08
     Slug
    0.08
    åī²
    0.08
    Activations Density 0.008%

    No Known Activations