© 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. 23696
    Prev
    Next
    INDEX
    Explanations

    folder management

    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
    -0.10
    vet
    -0.09
    --------------------------------
    -0.09
    ufs
    -0.09
    æµij身
    -0.09
    ãģĵãģ¨ãģĮãģ§ãģįãģ¾ãģĻ
    -0.08
    常å§Ķä¼ļ
    -0.08
    urt
    -0.08
    nings
    -0.08
    OTE
    -0.08
    POSITIVE LOGITS
    åĨħçļĦ
    0.11
    ial
    0.10
    åĴĮ个人
    0.10
    ç©°
    0.09
    ize
    0.09
    kart
    0.09
    apeut
    0.09
    åŃIJéĩĮ
    0.09
    ular
    0.09
    ordo
    0.09
    Activations Density 0.038%

    No Known Activations