© 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. 26893
    Prev
    Next
    INDEX
    Explanations

    useful in contexts of application

    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
    Ìģ
    -0.10
    åºĬä½į
    -0.10
     необÑħодим
    -0.09
    relevant
    -0.09
    æ¾Ī
    -0.09
    åĩºæĿ¥çļĦ
    -0.09
    éĻĮ
    -0.09
     responsibility
    -0.09
    å®ĺåı¸
    -0.08
    nbr
    -0.08
    POSITIVE LOGITS
    à¹ĥà¸Ļà¸ģาร
    0.13
    FUL
    0.12
    fully
    0.10
    /help
    0.10
    -looking
    0.10
     جدا
    0.10
    /prom
    0.10
    belt
    0.09
    åĥŃ
    0.09
    izo
    0.09
    Activations Density 0.044%

    No Known Activations