© 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. 32524
    Prev
    Next
    INDEX
    Explanations

    licensed contractors and insurance

    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
     whisk
    -0.09
     caves
    -0.09
    _UNLOCK
    -0.09
    æĮ½
    -0.09
    eka
    -0.08
    omm
    -0.08
    _BL
    -0.08
    éŸ
    -0.08
    æĢĢçĸij
    -0.08
    è¡£çī©
    -0.08
    POSITIVE LOGITS
    æĸ½å·¥
    0.15
    èĩªè´Ł
    0.13
    æĬ¥ä»·
    0.12
    èµĦè´¨
    0.12
    æī¿åĮħ
    0.11
    åĭ¤åĬ³
    0.11
    å·¥ç¨ĭè´¨éĩı
    0.10
    å¸ĪåĤħ
    0.10
     construction
    0.10
     воз
    0.10
    Activations Density 0.297%

    No Known Activations