© 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. 9833
    Prev
    Next
    INDEX
    Explanations

    advocate or activist

    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
    æĻº
    -0.09
    çĶŁåij½åij¨æľŁ
    -0.09
    .cmd
    -0.09
    æĺ¯çľŁçļĦ
    -0.09
    竦
    -0.09
    -overlay
    -0.09
    çĨ
    -0.09
    æī¾åĩĨ
    -0.09
    wis
    -0.08
    çĦĻ
    -0.08
    POSITIVE LOGITS
    åĢ¡å¯¼
    0.11
    é¢Ĩ
    0.10
    unts
    0.10
    è·µè¡Į
    0.10
     Marriott
    0.10
    代表
    0.10
    éłĺ
    0.09
     advocate
    0.09
    èĬĴ
    0.09
    éta
    0.09
    Activations Density 0.190%

    No Known Activations