© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20709
    Prev
    Next
    INDEX
    Explanations

    file systems and communications

    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
    讲æķħäºĭ
    -0.08
    æĥħåĨµè¿Ľè¡Į
    -0.08
    åīIJ
    -0.08
     تص
    -0.07
    0
    -0.07
    åıijå±ķä¸Ń
    -0.07
    burg
    -0.07
    樱
    -0.07
    jour
    -0.07
    1
    -0.07
    POSITIVE LOGITS
     Sims
    0.10
    æĺİæĺİ
    0.09
    лиÑĨ
    0.09
    çĶľç¾İ
    0.09
    ÑĢеÑģ
    0.08
    sgi
    0.08
    .mix
    0.08
    Ñģка
    0.08
    rig
    0.08
    ä¸ĢæŃ¥
    0.08
    Activations Density 0.277%

    No Known Activations