© 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. 49849
    Prev
    Next
    INDEX
    Explanations

    stranger demanding

    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
    空åīį
    -0.10
    èĢģ人家
    -0.10
    utions
    -0.09
    社ä¼ļ稳å®ļ
    -0.09
    icians
    -0.09
    rex
    -0.09
    ìį¨
    -0.09
    gers
    -0.09
    éĤ£äºº
    -0.09
    ÅĽci
    -0.09
    POSITIVE LOGITS
    hood
    0.12
    chrono
    0.09
    atto
    0.09
    å¸ļ
    0.09
    ties
    0.09
    ../../../
    0.09
    SHIP
    0.09
    izer
    0.09
    ../../../../
    0.09
    è¹
    0.08
    Activations Density 0.007%

    No Known Activations