© 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. 1130
    Prev
    Next
    INDEX
    Explanations

    BlackBerry Enterprise Service 10

    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
    structuring
    -0.10
     Existing
    -0.09
    çķĻè¨Ģ
    -0.09
    jual
    -0.09
    ØŃÙĪ
    -0.09
    quo
    -0.08
    éļIJ身
    -0.08
    飧
    -0.08
    客æĪ·æľįåĬ¡
    -0.08
    stor
    -0.08
    POSITIVE LOGITS
    çĪ±ä¸Ĭ
    0.10
    解éĶģ
    0.10
    ä¸ĢæĬĬ
    0.09
    çļ²
    0.09
    èľ¡
    0.09
    ä¸į解
    0.09
    åħ»èĢģ
    0.09
    è¿Ŀ纪
    0.09
    æŀ¯
    0.09
    fall
    0.08
    Activations Density 0.183%

    No Known Activations