© 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. 49211
    Prev
    Next
    INDEX
    Explanations

    Norwegian place names and people

    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
    ÐĺÐĿ
    -0.09
    æĹłæĦı
    -0.09
    æĮł
    -0.09
    eria
    -0.09
    amac
    -0.09
    æĹ¥è®°
    -0.09
    alia
    -0.09
    åł¡
    -0.08
    éĥĵ
    -0.08
    åĺ¤
    -0.08
    POSITIVE LOGITS
    thur
    0.09
    è¾Ľåĭ¤
    0.08
     denomination
    0.08
    dump
    0.08
    gaard
    0.08
    ëĭµ
    0.08
     olacaktır
    0.07
    -Trump
    0.07
     Vegas
    0.07
    onder
    0.07
    Activations Density 0.059%

    No Known Activations