© 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. 48249
    Prev
    Next
    INDEX
    Explanations

    amateur radio operator

    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
    abouts
    -0.09
    ated
    -0.08
    åħ¬è¯ģ
    -0.08
    Franc
    -0.08
    大æķ°æį®
    -0.08
    容
    -0.08
    uality
    -0.08
     trilogy
    -0.08
    ers
    -0.07
    idual
    -0.07
    POSITIVE LOGITS
    åĬĪ
    0.10
    .Future
    0.10
    rium
    0.09
    åŀ¤
    0.09
    DRV
    0.09
    åŃº
    0.09
    _WP
    0.09
    sparse
    0.09
    以å¾Į
    0.09
    kaar
    0.09
    Activations Density 0.002%

    No Known Activations