© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50459
    Prev
    Next
    INDEX
    Explanations

    voltage and measurement ranges

    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
    LAG
    -0.11
    åĩij
    -0.09
    pad
    -0.09
    hub
    -0.09
    edo
    -0.08
    è¾ĥå°ij
    -0.08
    å·²ç»ıæľī
    -0.08
    PAD
    -0.08
    èĵĿ天
    -0.08
    enes
    -0.08
    POSITIVE LOGITS
    é«ĺè¾¾
    0.12
    çļĦèĥ½åĬĽ
    0.10
    çĽİ
    0.10
    æľĢé«ĺ
    0.09
    Amazon
    0.09
    æĬµæĬĹ
    0.09
    ä¾Ī
    0.09
    大å¹ħæıIJåįĩ
    0.09
    ä¸įæŃ»
    0.09
    åķ¬
    0.09
    Activations Density 0.106%

    No Known Activations