© 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. 17072
    Prev
    Next
    INDEX
    Explanations

    Theiler's

    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
    ision
    -0.10
     ê·¸ëłĩì§Ģ
    -0.09
    illery
    -0.09
    ä¸ŃéĢĶ
    -0.09
    ulet
    -0.09
    obuf
    -0.08
     пов
    -0.08
    istani
    -0.08
     ÙĪاÙĦØ¥
    -0.08
    WithTitle
    -0.08
    POSITIVE LOGITS
    å·į
    0.10
    ãģ£ãģįãĤĬ
    0.09
    ร
    0.09
    éĩĩ访æŶ
    0.09
    ind
    0.09
     Moor
    0.09
    èĬ°
    0.09
    acter
    0.09
    _PP
    0.08
    çī¹æ´¾
    0.08
    Activations Density 0.099%

    No Known Activations