© 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. 38037
    Prev
    Next
    INDEX
    Explanations

    phoenix

    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
    æĺ¥ç§ĭ
    -0.09
    vertise
    -0.09
    ноп
    -0.09
    vant
    -0.09
    rina
    -0.09
     пÑĢинÑı
    -0.08
    ÑģÑĤв
    -0.08
    antu
    -0.08
    iba
    -0.08
    odesk
    -0.08
    POSITIVE LOGITS
    èĪ¬çļĦ
    0.10
    Phoenix
    0.10
    åĽŀçŃĶ
    0.09
    èĪ¬
    0.09
    åĩ¤åĩ°
    0.08
    åĩºåĩ»
    0.08
    å´Ľèµ·
    0.08
    charm
    0.08
    èĥ½ä½¿
    0.08
    pit
    0.08
    Activations Density 0.009%

    No Known Activations