© 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. 21928
    Prev
    Next
    INDEX
    Explanations

    na na na

    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
     ÑĢеÑĪа
    -0.09
    èĩªèº«
    -0.09
    zen
    -0.09
    ëģĦ
    -0.09
    çİĩè¾¾
    -0.08
    ifr
    -0.08
    两次
    -0.08
    agara
    -0.08
    èĩªèº«çļĦ
    -0.08
    okit
    -0.08
    POSITIVE LOGITS
    以èĩ³äºİ
    0.10
    é¹Ń
    0.09
    .'_
    0.08
    ankan
    0.08
     Ost
    0.08
    趾
    0.08
    管å§Ķä¼ļ
    0.08
    rap
    0.08
    _pb
    0.08
    jac
    0.08
    Activations Density 0.096%

    No Known Activations