© 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. 49427
    Prev
    Next
    INDEX
    Explanations

    quality of life

    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
    esa
    -0.10
    alyzer
    -0.09
    cie
    -0.09
    icit
    -0.09
     PROF
    -0.09
    è·£
    -0.09
    æĽ·
    -0.09
    ication
    -0.09
    sWith
    -0.09
    esk
    -0.09
    POSITIVE LOGITS
    te
    0.09
    æĪ³
    0.09
    ities
    0.09
    éĺĹ
    0.09
    erno
    0.09
    mine
    0.09
    Ĭ
    0.08
    ÑĤÑĢ
    0.08
    ä¸įä½³
    0.08
    çĬ¶åĨµ
    0.08
    Activations Density 0.046%

    No Known Activations