© 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. 18701
    Prev
    Next
    INDEX
    Explanations

    songs, verses, refrain

    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
     Lang
    -0.09
    Lang
    -0.09
    lang
    -0.09
     Shaw
    -0.08
    èĥĮ
    -0.08
    irs
    -0.08
    çĬ¶åĨµ
    -0.08
    APS
    -0.08
    è¿Ļ件
    -0.08
    åľĴ
    -0.08
    POSITIVE LOGITS
    æľŁ
    0.09
    .deploy
    0.09
    éĥľ
    0.09
    人人éĥ½
    0.08
    åĬłä¸Ĭ
    0.08
    èIJ½
    0.08
    é¦Ļæ°´
    0.08
    rophe
    0.08
    ,List
    0.08
    BOOLE
    0.08
    Activations Density 0.017%

    No Known Activations