© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8906
    Prev
    Next
    INDEX
    Explanations

    streets and roads

    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
    é¢Ĩ
    -0.11
    ä¸Ģåij³
    -0.09
    ä¸Ģæľ¬
    -0.09
    ড
    -0.09
    mia
    -0.09
    åĽ´
    -0.09
    èĹı
    -0.09
    oard
    -0.09
    ä¾Ŀ
    -0.09
    atten
    -0.08
    POSITIVE LOGITS
    è¡Ĺéģĵ
    0.23
     streets
    0.20
    è¡Ĺ头
    0.20
    è¡Ĺä¸Ĭ
    0.19
     street
    0.19
     Street
    0.17
    大è¡Ĺ
    0.17
    street
    0.16
    è¡Ĺ
    0.16
     STREET
    0.16
    Activations Density 0.083%

    No Known Activations