© 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. 48333
    Prev
    Next
    INDEX
    Explanations

    Sierra Leone conflict, Exchange, issue

    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
    ouro
    -0.10
     ÑĢаÑģÑħод
    -0.09
    .addListener
    -0.09
    ç¿ħ
    -0.08
    çĵł
    -0.08
    rell
    -0.08
     Pref
    -0.08
    pref
    -0.08
    管
    -0.08
     Pods
    -0.08
    POSITIVE LOGITS
    msp
    0.09
    被èªī
    0.09
    æ¥ļ
    0.08
    è§ģ解
    0.08
    andom
    0.08
    éĴĿ
    0.08
    æĴij
    0.08
     اÙĦÙħÙĪا
    0.08
    ìĿĮìĿĦ
    0.08
     Bang
    0.08
    Activations Density 0.182%

    No Known Activations