© 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. 56678
    Prev
    Next
    INDEX
    Explanations

    adults are

    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
    asher
    -0.10
    çħ§äº®
    -0.09
    éĻªçĿĢ
    -0.09
    otech
    -0.08
    ç»°
    -0.08
    æ²Ľ
    -0.08
    èĬ±èįī
    -0.08
    åİ¥
    -0.08
    éħįå¤ĩäºĨ
    -0.08
    nano
    -0.08
    POSITIVE LOGITS
    خت
    0.09
    è¯
    0.08
    åı¯è¾¾
    0.08
    辫
    0.08
    è¡Į人
    0.08
    çŃĴ
    0.08
    人工
    0.07
    åĪ©çĶ¨çİĩ
    0.07
    çªģåĩ»
    0.07
    inia
    0.07
    Activations Density 0.250%

    No Known Activations