© 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. 61710
    Prev
    Next
    INDEX
    Explanations

    "am" followed by adverbial complement

    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
    ski
    -0.10
    swith
    -0.09
    _APPS
    -0.09
    ган
    -0.09
    ĭ
    -0.09
    ansom
    -0.09
    Ò£
    -0.09
    ìĬ¬
    -0.09
    æĪijçĪ±ä½ł
    -0.09
    æĿĸ
    -0.09
    POSITIVE LOGITS
     meisten
    0.11
     besten
    0.10
    az
    0.09
    ERICAN
    0.09
    å¥Ĥ
    0.09
    plitude
    0.09
    平常
    0.09
    ixture
    0.08
    è¾Ķ
    0.08
     sure
    0.08
    Activations Density 0.072%

    No Known Activations