© 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. 63086
    Prev
    Next
    INDEX
    Explanations

    city names and locations

    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
    ле
    -0.08
     bis
    -0.08
    ä¸Ģå°ı
    -0.08
    æĬķæľº
    -0.08
    æĺ¯ä¸Ģç§į
    -0.08
    ä¸Ģ大åłĨ
    -0.08
    bis
    -0.08
    ä¹Łæĺ¯ä¸Ģç§į
    -0.08
    æīįæľī
    -0.08
    åĵĪå°Ķ
    -0.08
    POSITIVE LOGITS
    åľ¨æĪijåĽ½
    0.09
    æķ£çĥŃ
    0.08
    åľ¨æĪij
    0.08
    BOR
    0.08
    èĶ·
    0.08
    urat
    0.08
     hostage
    0.08
    DMIN
    0.08
    èĮķ
    0.08
    /Documents
    0.08
    Activations Density 0.154%

    No Known Activations