© 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. 33786
    Prev
    Next
    INDEX
    Explanations

    independent living, filmmaker, music, game, travel

    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
    gether
    -0.09
    ting
    -0.09
    owing
    -0.09
    裱
    -0.09
    /her
    -0.09
    ãĤ£
    -0.08
    wake
    -0.08
    ween
    -0.08
    çĪ¸
    -0.08
    roc
    -0.08
    POSITIVE LOGITS
    -minded
    0.16
     minded
    0.14
    æĢ§å¼º
    0.12
    人士
    0.11
    zza
    0.10
    iates
    0.10
    ität
    0.09
    iat
    0.09
    calar
    0.09
    第ä¸īæĸ¹
    0.09
    Activations Density 0.025%

    No Known Activations