© 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. 31512
    Prev
    Next
    INDEX
    Explanations

    beacon hill road street tests

    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
    оÑĢÑĤ
    -0.10
    ablo
    -0.10
     ê²
    -0.09
    oucher
    -0.09
    ango
    -0.09
    most
    -0.09
    anka
    -0.09
     каж
    -0.08
    ugh
    -0.08
    ulk
    -0.08
    POSITIVE LOGITS
    uci
    0.09
    éľīç´ł
    0.09
    eer
    0.09
    ../../../
    0.09
    anda
    0.09
    亢
    0.09
    -eyed
    0.09
    /at
    0.09
    çģ¼
    0.08
    çģ¯
    0.08
    Activations Density 0.009%

    No Known Activations