© 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. 23708
    Prev
    Next
    INDEX
    Explanations

    hardware components

    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
    éĢĶ
    -0.10
    å¨ĥ
    -0.09
    çĶŁæ´»çļĦ
    -0.09
    纡
    -0.09
    _IMPLEMENT
    -0.09
    implements
    -0.09
    æĹ¥æĬ¥
    -0.08
    尽头
    -0.08
    scape
    -0.08
     cio
    -0.08
    POSITIVE LOGITS
    座
    0.10
    å¤Ħ
    0.09
    -less
    0.09
    less
    0.08
    _iface
    0.08
    æĮ¤
    0.08
    çļĦåĬ¨ä½ľ
    0.08
    ToPoint
    0.08
    çĸ¾
    0.08
    oret
    0.08
    Activations Density 0.145%

    No Known Activations