© 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. 4761
    Prev
    Next
    INDEX
    Explanations

    here followed by context

    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
    irk
    -0.10
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.09
    å½ĵåĪĿ
    -0.09
    elib
    -0.09
    åĪ°æŶåĢĻ
    -0.09
    è¿Ļæīįæĺ¯
    -0.09
    ä¸Ģä¸ĸ
    -0.08
    pit
    -0.08
    _TEX
    -0.08
    说å®Į
    -0.08
    POSITIVE LOGITS
    after
    0.09
    æīĢèĥ½
    0.09
    åħ¹
    0.09
    enas
    0.08
    WebKit
    0.08
    æĺĻ
    0.08
    arent
    0.08
    MAND
    0.08
    bei
    0.08
     Cyr
    0.08
    Activations Density 0.048%

    No Known Activations