© 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. 23045
    Prev
    Next
    INDEX
    Explanations

    not followed by verb

    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
    åİ»åĵªåĦ¿
    -0.09
    èĪªæµ·
    -0.09
     Rising
    -0.09
    çķıæĥ§
    -0.08
    oa
    -0.08
     Wor
    -0.08
    åıĹå½±åĵį
    -0.08
    æĹ¢åı¯ä»¥
    -0.08
    æĢķ
    -0.08
    åĪĢ
    -0.08
    POSITIVE LOGITS
    å®ŀæŶ
    0.10
    å®Įç¾İ
    0.09
     Tun
    0.08
    å¾®
    0.08
    å®Įæķ´
    0.08
    太快
    0.08
    é½IJåħ¨
    0.08
    ä¸Ģå®ļèĥ½
    0.08
    kan
    0.08
    rust
    0.08
    Activations Density 0.028%

    No Known Activations