© 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. 27791
    Prev
    Next
    INDEX
    Explanations

    recycle, find out, see the, all rights, wanderlust, please login

    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
    “
    -0.09
    è¿Ļåħ¶ä¸Ń
    -0.08
    omes
    -0.08
    æķijåij½
    -0.08
    ft
    -0.08
    æĻ®åıĬ
    -0.08
    åIJĮæŶè¿ĺ
    -0.08
    orian
    -0.08
    å©ķ
    -0.08
    íĦ´
    -0.08
    POSITIVE LOGITS
     zwar
    0.12
    ä¸Ģæĸ¹éĿ¢æĺ¯
    0.10
    æľįåĭĻæĪĸ
    0.10
    çľĭä»ĸ
    0.09
    说ä»Ģä¹Ī
    0.09
    ScreenState
    0.08
    åıijè´¢
    0.08
    æľĥåĵ¡è¨»åĨĬ
    0.08
    åħ¥çĿ¡
    0.08
    apg
    0.08
    Activations Density 0.648%

    No Known Activations