© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50722
    Prev
    Next
    INDEX
    Explanations

    Lei Ni, Ivan Blitz, U. Brutkiewicz, Raiders, Coup, Maulvi Nazir, Lara Mussell, Citadel Media

    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
    ings
    -0.12
    ãģĹãģ¾ãģĨ
    -0.11
     dÃłng
    -0.10
    ĺ
    -0.09
    INGS
    -0.09
     converse
    -0.09
    mates
    -0.09
    /mac
    -0.09
    zier
    -0.09
    forming
    -0.09
    POSITIVE LOGITS
    oise
    0.11
    naire
    0.10
     liá»ĩt
    0.09
    诳
    0.09
    æ»ĵ
    0.09
    ä¸įçĦ¶
    0.09
    @student
    0.09
    oft
    0.08
    ted
    0.08
    æīĵåĵį
    0.08
    Activations Density 0.152%

    No Known Activations