© 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. 30301
    Prev
    Next
    INDEX
    Explanations

    people

    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
    èĩ¾
    -0.13
     paran
    -0.09
    çļĦåĬŀæ³ķ
    -0.09
    lef
    -0.09
    人éĢī
    -0.08
    åIJĦåľ°
    -0.08
    ä¸įå·²
    -0.08
    -haired
    -0.08
    人å±ħ
    -0.08
    ê°Ŀ
    -0.08
    POSITIVE LOGITS
    hood
    0.13
    aled
    0.11
    vern
    0.10
    ÑĪки
    0.10
    èįĥ
    0.10
    代表大ä¼ļ
    0.10
    èĪ¸
    0.09
    åĿŀ
    0.09
    ç±ģ
    0.09
    微信åı·
    0.09
    Activations Density 0.075%

    No Known Activations