© 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. 31761
    Prev
    Next
    INDEX
    Explanations

    time stamps, dates, acronyms

    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
    ,
    -0.07
    æ´»åĬĽ
    -0.07
    :
    -0.07
    ipo
    -0.07
    (
    -0.07
    åIJĦåĮº
    -0.07
    opoulos
    -0.07
    -
    -0.07
    izz
    -0.07
    ./
    -0.06
    POSITIVE LOGITS
    cmds
    0.10
     èĭ¥è¦ģ
    0.10
    ï¸
    0.10
    _VC
    0.10
    .sg
    0.10
    çµķ
    0.10
    樹
    0.10
    åħļæĢ»
    0.09
    çħĮ
    0.09
    iddleware
    0.09
    Activations Density 2.568%

    No Known Activations