© 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. 9463
    Prev
    Next
    INDEX
    Explanations

    street names or 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
    åł°
    -0.10
    åĵģå¾·
    -0.10
     полÑĮзÑĥ
    -0.09
    æIJ¬
    -0.09
    èĢģå©Ĩ
    -0.09
    è¿Ļä¹Īå¤ļ
    -0.09
    idata
    -0.08
    åĨĴéĻ©
    -0.08
    иÑĤел
    -0.08
    ASI
    -0.08
    POSITIVE LOGITS
    BUS
    0.09
    æģĴ
    0.08
     Stap
    0.08
    欢è¿İ大家
    0.08
    纯
    0.08
    enko
    0.08
    ä¸Ģ家
    0.08
     border
    0.07
    ä¸Ģä¸ĭ
    0.07
    ubb
    0.07
    Activations Density 0.080%

    No Known Activations