© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38498
    Prev
    Next
    INDEX
    Explanations

    Armagh

    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
    åıįè¿ĩæĿ¥
    -0.10
    产èĥ½
    -0.10
    paren
    -0.09
    noon
    -0.09
    ä»ĵä½į
    -0.09
    оваÑĢ
    -0.09
    Holy
    -0.09
    åħļä¸Ń央
    -0.09
    æ´½
    -0.09
    æµģæ°´
    -0.09
    POSITIVE LOGITS
    åijĺ
    0.08
    elts
    0.08
    åĵ¡
    0.08
    æģª
    0.08
    çīĮ
    0.08
    çĽİ
    0.08
    rup
    0.08
    éĺľ
    0.08
    andom
    0.07
    aat
    0.07
    Activations Density 0.002%

    No Known Activations