© 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. 33498
    Prev
    Next
    INDEX
    Explanations

    I'm/am having trouble

    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
    ful
    -0.09
    篱
    -0.09
    è¿·
    -0.08
    åĪĨæĺİ
    -0.08
    rib
    -0.08
    åĵģè´¨
    -0.08
    æħķ
    -0.08
    åıĤ
    -0.08
     Burl
    -0.08
    åı¯æݧ
    -0.08
    POSITIVE LOGITS
    ä»»åĭĻ
    0.10
    iaux
    0.10
    çļĦä»»åĬ¡
    0.09
    èĿĮ
    0.09
    好å¥ĩ
    0.09
    /disc
    0.09
    è¦ģä¹Ī
    0.09
    éĴµ
    0.09
    steller
    0.09
    éĴĬ
    0.09
    Activations Density 0.005%

    No Known Activations