© 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. 63645
    Prev
    Next
    INDEX
    Explanations

    aluminum and aluminum alloys

    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
    anium
    -0.10
    éĢŀ
    -0.09
    ually
    -0.09
    оÑĤов
    -0.09
    顼
    -0.09
    liest
    -0.09
    .cz
    -0.09
    åĴĮåľ°åĮº
    -0.09
    iros
    -0.09
    诮
    -0.08
    POSITIVE LOGITS
    ç®Ķ
    0.12
     alloy
    0.09
    æĭľ
    0.09
    åĪ¶åĵģ
    0.09
    -bodied
    0.09
     foil
    0.08
    -fluid
    0.08
    ambda
    0.08
    éro
    0.08
    åīĶ
    0.08
    Activations Density 0.013%

    No Known Activations