© 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. 63146
    Prev
    Next
    INDEX
    Explanations

    solely, simply, just, purely

    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
    迦
    -0.10
    .annotate
    -0.10
    ISTA
    -0.09
     Aub
    -0.09
     informal
    -0.09
    otropic
    -0.09
    ãģĹãģ°
    -0.09
    .fake
    -0.08
    å¾Īæľīåı¯èĥ½
    -0.08
    åĴĮçĿ¦
    -0.08
    POSITIVE LOGITS
    åįķ纯çļĦ
    0.14
    ä¸Ģåij³
    0.14
    mere
    0.12
    åįķ纯
    0.12
    åģľçķĻåľ¨
    0.11
    çľĭå¾ħ
    0.11
    ä¾ĿéĿł
    0.10
    纯粹
    0.10
    ä»ħä»ħ
    0.10
    çĽ²çĽ®
    0.10
    Activations Density 0.089%

    No Known Activations