© 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. 58443
    Prev
    Next
    INDEX
    Explanations

    numbers followed by words

    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
    è¿ĻäºĽéĹ®é¢ĺ
    -0.09
    Markup
    -0.09
    尤为éĩįè¦ģ
    -0.09
    hammer
    -0.09
    çĦ¶èĢĮ
    -0.09
    çĥ¹
    -0.09
    大åĬĽæİ¨è¿Ľ
    -0.09
    è¿ĻçĤ¹
    -0.08
    尤为
    -0.08
    fts
    -0.08
    POSITIVE LOGITS
    åģľçķĻåľ¨
    0.09
     bland
    0.09
    udes
    0.09
     bask
    0.08
    ä¼ļåľ¨
    0.08
    bes
    0.08
    ouch
    0.08
    ViewItem
    0.08
    碴
    0.08
     RESP
    0.08
    Activations Density 0.029%

    No Known Activations