© 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. 31481
    Prev
    Next
    INDEX
    Explanations

    control, management, care, service, network, brand, level

    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
    们éĥ½
    -0.10
    们
    -0.10
    еле
    -0.10
    åħ®
    -0.10
    们çļĦ
    -0.10
    ä¿¡æģ¯æľįåĬ¡
    -0.09
    çĮ·
    -0.09
    ä¸ĢçĤ¹çĤ¹
    -0.08
    éķĴ
    -0.08
    ä¼ĹæīĢ
    -0.08
    POSITIVE LOGITS
    enta
    0.10
    nder
    0.10
     Cord
    0.09
    é¬ĵ
    0.09
     Hastings
    0.09
    绣çŃ¹æİ¨è¿Ľ
    0.08
    èĢģå¦Ī
    0.08
    odel
    0.08
    mania
    0.08
    éĵ¶
    0.08
    Activations Density 0.179%

    No Known Activations