© 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. 50620
    Prev
    Next
    INDEX
    Explanations

    not understood or not clear

    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
    为æĤ¨æıIJä¾Ľ
    -0.09
    èĩªæĿ¥
    -0.09
    æĿ¥æºIJäºİ
    -0.09
    èĥ½æī¾åĪ°
    -0.09
    èĥ½çľĭåĪ°
    -0.08
    åīįçŀ»
    -0.08
    éļ¾åħ³
    -0.08
    èĥ½å¤Łåľ¨
    -0.08
    loo
    -0.08
    isd
    -0.08
    POSITIVE LOGITS
    诸
    0.10
    çĭİ
    0.09
    å°
    0.09
     лид
    0.09
    éĥ¨ä½į
    0.09
    深深çļĦ
    0.08
    PointSize
    0.08
    npos
    0.08
    ucas
    0.08
    operands
    0.08
    Activations Density 0.408%

    No Known Activations