© 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. 51214
    Prev
    Next
    INDEX
    Explanations

    Olympia and Olympus variations

    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
    åİ¢
    -0.10
    ymes
    -0.09
    çīĸ
    -0.09
    inel
    -0.09
    LIN
    -0.09
    аÑİÑĤÑģÑı
    -0.08
    åĦ¿
    -0.08
    æ°´ä¸Ĭ
    -0.08
    绶
    -0.08
    DDL
    -0.08
    POSITIVE LOGITS
    ically
    0.09
    iad
    0.09
    人çī©
    0.09
    ical
    0.09
    ester
    0.09
    Ñīен
    0.09
    кл
    0.09
    platz
    0.09
    ICAL
    0.09
    ens
    0.09
    Activations Density 0.007%

    No Known Activations