© 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. 18197
    Prev
    Next
    INDEX
    Explanations

    New Mexico cities

    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
    зи
    -0.09
    æ·ŀ
    -0.09
    .encoding
    -0.09
    èĭĵ
    -0.09
    avian
    -0.09
    çĭ®åŃIJ
    -0.09
    翳
    -0.09
    羡
    -0.09
    atical
    -0.09
    Boston
    -0.08
    POSITIVE LOGITS
     Albuquerque
    0.12
    Adobe
    0.10
     Adobe
    0.10
    åľ£åľ°
    0.09
    lot
    0.09
     returnUrl
    0.09
    dam
    0.09
    buquerque
    0.08
    èݲ
    0.08
    angu
    0.08
    Activations Density 0.119%

    No Known Activations