© 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. 52854
    Prev
    Next
    INDEX
    Explanations

    interim or temporary roles/solutions

    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
    åij¨åĪĬ
    -0.10
    çĭİ
    -0.09
    icl
    -0.09
    éģĺ
    -0.09
    åı¸é©¬
    -0.09
    åħ¨è¿ĩç¨ĭ
    -0.08
    åı¸
    -0.08
    æµģåĩº
    -0.08
    åĬ³åĬ¡
    -0.08
    wald
    -0.08
    POSITIVE LOGITS
    临æŶ
    0.18
    æļĤ
    0.16
    è¿ĩ渡
    0.16
    æļĤæŶ
    0.16
     temporary
    0.15
     interim
    0.14
    Temporary
    0.14
     Temporary
    0.14
    åºĶæĢ¥
    0.13
     tạm
    0.13
    Activations Density 0.104%

    No Known Activations