© 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. 21643
    Prev
    Next
    INDEX
    Explanations

    world leaders and political figures

    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
     Vog
    -0.09
    çĪ±ä½ł
    -0.09
    iry
    -0.09
    èĮ«çĦ¶
    -0.09
    ply
    -0.09
    çĻ¾èĬ±
    -0.09
    çļĦåģļæ³ķ
    -0.08
    ä½įåĪĹ
    -0.08
    éģįå¸ĥ
    -0.08
    çĶ°åĽŃ
    -0.08
    POSITIVE LOGITS
    astes
    0.09
    ections
    0.08
    ortal
    0.08
    å®ľ
    0.08
    æĭ¯
    0.08
    éĢµ
    0.08
    otime
    0.07
    æļ®
    0.07
    ective
    0.07
    ç»·
    0.07
    Activations Density 0.008%

    No Known Activations