© 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. 22443
    Prev
    Next
    INDEX
    Explanations

    financial periods

    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
    mith
    -0.09
    èĥ
    -0.09
    åĪ°æŶåĢĻ
    -0.09
    éĤ£æł·
    -0.08
    .cond
    -0.08
    æĺİ天
    -0.08
    enheim
    -0.08
    _evt
    -0.08
    åĬ±
    -0.08
    å¸Ŀ
    -0.08
    POSITIVE LOGITS
    åĮºéĹ´
    0.10
    ingly
    0.10
    alone
    0.09
    /latest
    0.09
    orate
    0.09
    æľĢå¿«çļĦ
    0.09
    çļĦåį°è±¡
    0.09
    crm
    0.08
    -archive
    0.08
    æľĢç¾İçļĦ
    0.08
    Activations Density 0.047%

    No Known Activations