© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6025
    Prev
    Next
    INDEX
    Explanations

    just followed by "one", "a", or for

    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
    ãģ¡ãĤĩãģĨãģ©
    -0.11
    èĻ½çĦ¶
    -0.10
    ä¸įåİ»
    -0.10
    è¿Ļæł·è¯´
    -0.09
    è°ħ
    -0.09
     chances
    -0.09
    åį³ä½¿
    -0.09
    èĻ½
    -0.09
    illage
    -0.09
     há»ĵi
    -0.09
    POSITIVE LOGITS
    ifiable
    0.16
    ifications
    0.13
    ifying
    0.12
    ifi
    0.11
    å±ĢéĻIJäºİ
    0.10
    ifikasi
    0.09
    ness
    0.09
    ifiers
    0.09
    ä½ľèĢħæľ¬äºº
    0.09
     kidding
    0.09
    Activations Density 0.077%

    No Known Activations