© 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. 49598
    Prev
    Next
    INDEX
    Explanations

    county names and regions

    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
    èĥ½çľĭåĩº
    -0.10
    æŃ»äºĨ
    -0.09
    æĮĤåľ¨
    -0.09
    çĪ±åĽ½ä¸»ä¹ī
    -0.09
    ä¸įéĶĻ
    -0.09
    ä¸Ģ年级
    -0.08
    ä½ľèĢħæīĢæľī
    -0.08
    æĿijåŃIJ
    -0.08
    å¹²äºĭ
    -0.08
    转移åĪ°
    -0.08
    POSITIVE LOGITS
    éĥ¡
    0.10
    çľĮ
    0.10
    seys
    0.10
    SCO
    0.10
    cala
    0.09
    Closure
    0.09
     Slee
    0.09
     closures
    0.09
    åİ¿
    0.09
    rag
    0.09
    Activations Density 0.164%

    No Known Activations