© 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. 1099
    Prev
    Next
    INDEX
    Explanations

    material structure and phase analyses

    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
     оÑĢг
    -0.10
    解æķ£
    -0.10
    _UID
    -0.09
    åįĬ天
    -0.09
    ÐŀÐł
    -0.09
    eree
    -0.09
    atedRoute
    -0.09
    æĶ¾æīĭ
    -0.08
     Cotton
    -0.08
    .hover
    -0.08
    POSITIVE LOGITS
    æĻ¶
    0.10
     defect
    0.09
     mach
    0.09
     weld
    0.09
    缺éĻ·
    0.09
     grain
    0.09
     defects
    0.08
     emb
    0.08
    æľįå½¹
    0.08
    çĦĬ
    0.08
    Activations Density 0.280%

    No Known Activations