© 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. 38962
    Prev
    Next
    INDEX
    Explanations

    Ottawa and Wellington and Ottoman

    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
    éĻIJæľŁ
    -0.10
    loth
    -0.09
    undy
    -0.09
    /vnd
    -0.09
    otti
    -0.09
    ods
    -0.09
    agara
    -0.09
    å¿ĥ头
    -0.08
    æľīè¶³å¤ŁçļĦ
    -0.08
    pard
    -0.08
    POSITIVE LOGITS
    licht
    0.10
    ðŁı»
    0.10
    ayo
    0.09
    ðŁı¼
    0.09
    ted
    0.09
    OrCreate
    0.09
    æ³Ħ
    0.08
    è§Ĵ
    0.08
     trữ
    0.08
    asher
    0.08
    Activations Density 0.008%

    No Known Activations