© 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. 62637
    Prev
    Next
    INDEX
    Explanations

    carameletto, barigazzo, fire stations, factories

    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
    ãģĹãģ¾ãģĨ
    -0.11
    keeper
    -0.10
    èĪ¶
    -0.09
    anness
    -0.08
    æ¯Ķäºļ
    -0.08
    iven
    -0.08
    çĭłæĬĵ
    -0.08
    acity
    -0.08
    annels
    -0.08
    erties
    -0.08
    POSITIVE LOGITS
    ized
    0.12
    æ±ģ
    0.10
    TestFixture
    0.09
    oad
    0.09
    ine
    0.09
    æŁIJç§įç¨ĭ度
    0.09
     Zucker
    0.09
    ated
    0.08
    zig
    0.08
    _SIG
    0.08
    Activations Density 0.004%

    No Known Activations