© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36315
    Prev
    Next
    INDEX
    Explanations

    streets and surrounding areas

    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
    rom
    -0.10
    大家éĥ½
    -0.09
    cil
    -0.09
    åįģ足
    -0.09
    erus
    -0.08
    éĢĿ
    -0.08
    é©Ń
    -0.08
    IAS
    -0.08
    çļĤ
    -0.08
    ero
    -0.08
    POSITIVE LOGITS
    chod
    0.10
    æĿĤçī©
    0.09
    WithValue
    0.09
     Streets
    0.09
    ä¸ĬçļĦ
    0.09
    æĸ°æĺ¥
    0.09
    çĬ¹
    0.09
    çłĸ
    0.09
    çĤİ
    0.09
    unes
    0.08
    Activations Density 0.010%

    No Known Activations