© 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. 11056
    Prev
    Next
    INDEX
    Explanations

    headphone/phone related audio devices

    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
    ly
    -0.11
    lings
    -0.10
    atoon
    -0.10
    bsp
    -0.09
    estro
    -0.09
    atable
    -0.08
    ution
    -0.08
    çļĦçľ¼åħī
    -0.08
    atform
    -0.08
    isms
    -0.08
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.10
    çĸ½
    0.09
    åıĬ缸åħ³
    0.09
    ä¸ĢæĹı
    0.09
    athom
    0.09
    .twig
    0.09
    ilon
    0.09
    ä»ĺãģį
    0.09
    ä½İ碳
    0.08
    åIJ¡
    0.08
    Activations Density 0.008%

    No Known Activations