© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37116
    Prev
    Next
    INDEX
    Explanations

    in connection with

    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
    åĬĪ
    -0.09
    ÑĤÑĮ
    -0.09
     пÑĢинима
    -0.08
     tact
    -0.08
    rom
    -0.08
    èĽĻ
    -0.08
    æĬ¼éĩij
    -0.08
    -0.08
    åĴĮæĬĢæľ¯
    -0.08
    rock
    -0.08
    POSITIVE LOGITS
    KeyEvent
    0.10
    stå
    0.09
     Bernardino
    0.09
    赶
    0.09
    æĢ»åħ¬åı¸
    0.09
    åĭĥåĭĥ
    0.08
    abouts
    0.08
    æľīè¿ĩ
    0.08
    aja
    0.08
    TagName
    0.08
    Activations Density 0.013%

    No Known Activations