© 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. 58016
    Prev
    Next
    INDEX
    Explanations

    Maid Park, Gates said, Clancy books

    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
    rst
    -0.09
    plements
    -0.08
     Ret
    -0.08
    çķĻåŃĺ
    -0.08
    伸æīĭ
    -0.08
    çģ¿çĥĤ
    -0.08
    IgnoreCase
    -0.08
     inch
    -0.08
    éħĮ
    -0.08
    éªĩ
    -0.08
    POSITIVE LOGITS
    åĴ©
    0.09
    楼ä¸ĭ
    0.09
    panse
    0.09
    icom
    0.09
    edin
    0.09
    åķĥ
    0.08
     viet
    0.08
    åĪ¨
    0.08
    iao
    0.08
    ighter
    0.08
    Activations Density 0.003%

    No Known Activations