© 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. 20189
    Prev
    Next
    INDEX
    Explanations

    waterfall or Niagara Falls

    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
    æĬ¬èµ·
    -0.09
    iddles
    -0.09
    à¸ĵา
    -0.09
    æŁı
    -0.09
    thane
    -0.09
    å°ģ
    -0.09
    éļıä¹ĭ
    -0.09
    è°į
    -0.08
    ç¼Ŀ
    -0.08
    apers
    -0.08
    POSITIVE LOGITS
    çĢijå¸ĥ
    0.20
    çĢij
    0.17
     waterfall
    0.15
    æ°´æµģ
    0.13
    ä¸ī峡
    0.10
    æµģéĩı
    0.10
    æĤ¬å´ĸ
    0.10
     Niagara
    0.10
     Falls
    0.10
    alia
    0.10
    Activations Density 0.048%

    No Known Activations