© 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. 61525
    Prev
    Next
    INDEX
    Explanations

    may use or can use

    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
    uest
    -0.08
    åĬłæ²¹
    -0.08
    éķ¿çŁŃ
    -0.08
    å´Ľ
    -0.08
    çŁŃ
    -0.08
    鸳
    -0.08
    æľīä¸ĢçĤ¹
    -0.08
    å·§
    -0.08
    ä¸ĵä¸ļåĮĸ
    -0.08
     sqr
    -0.07
    POSITIVE LOGITS
    DED
    0.10
    åĿij
    0.09
    hana
    0.09
    MapView
    0.09
    ä»Ĭ天æĪij们
    0.08
    äºŃ
    0.08
    çĵ¶åŃIJ
    0.08
    Shield
    0.08
    leet
    0.08
    _lot
    0.08
    Activations Density 0.004%

    No Known Activations