© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52866
    Prev
    Next
    INDEX
    Explanations

    with food and time

    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
    æ»´æ»´
    -0.09
    idl
    -0.09
    mars
    -0.08
    liga
    -0.08
    è¯ĦåĪ¤
    -0.08
    çıł
    -0.08
    ç¡ķ
    -0.08
    iable
    -0.08
    çģ¯åħ·
    -0.08
    apk
    -0.08
    POSITIVE LOGITS
     Affero
    0.09
    éħįå¥Ĺ
    0.09
     timing
    0.09
    产ä¸ļåĮĸ
    0.09
    å½ĵæĪIJ
    0.09
    åĿ¼
    0.09
    éĥ¨
    0.09
    èĪ«
    0.08
    æĦŁè§īåĪ°
    0.08
    ä¸į便
    0.08
    Activations Density 0.039%

    No Known Activations