© 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. 56719
    Prev
    Next
    INDEX
    Explanations

    PO

    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
    éĥ¡
    -0.09
    æľĢåIJİä¸Ģ次
    -0.09
    è¡¡éĩı
    -0.09
    é¦ĸ次
    -0.09
     ìľĦíķľ
    -0.09
    å¤ľéĩĮ
    -0.09
    è¦ģä¸įçĦ¶
    -0.08
    /op
    -0.08
    åĮĸè¿Ľç¨ĭ
    -0.08
    ason
    -0.08
    POSITIVE LOGITS
    tron
    0.09
    issy
    0.09
     اÙĦÙĨÙĤد
    0.08
    éļı
    0.08
    Impossible
    0.08
    thing
    0.08
    é£İæĻ¯
    0.08
    Ke
    0.08
    alette
    0.08
     Ke
    0.08
    Activations Density 0.008%

    No Known Activations