© 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. 17665
    Prev
    Next
    INDEX
    Explanations

    located at

    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
    7
    -0.08
    6
    -0.08
    5
    -0.08
    4
    -0.08
    ä¿İ
    -0.08
     dere
    -0.08
    æ·±æ¸Ĭ
    -0.08
    Ñıм
    -0.08
    aps
    -0.08
    9
    -0.08
    POSITIVE LOGITS
    ä¸Ģæī¹
    0.10
    ÙĤد
    0.09
    _argument
    0.09
    åįķ纯
    0.09
    idel
    0.08
    对èĩªå·±
    0.08
     Ä°ki
    0.08
     Sachs
    0.08
    MH
    0.08
    gado
    0.08
    Activations Density 1.390%

    No Known Activations