© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22104
    Prev
    Next
    INDEX
    Explanations

    provost, provocation, provender, providential, provender

    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
    bbing
    -0.09
    èĴ½
    -0.09
    åĪ¨
    -0.09
    ãģ£ãģįãĤĬ
    -0.09
    è¾¹éĻħ
    -0.09
    顾éĹ®
    -0.08
    åĪ¶åĵģ
    -0.08
    æĿ¥èĩªäºİ
    -0.08
    å¾Ĺèµ·
    -0.08
    åĩĢåľŁ
    -0.08
    POSITIVE LOGITS
    iana
    0.13
    ry
    0.10
    stown
    0.10
    aires
    0.10
    ä¸Ģåı¥
    0.10
    婦
    0.09
    iens
    0.09
    ãĥĹãĥªãĥ³
    0.09
    ial
    0.09
     reconciliation
    0.09
    Activations Density 0.006%

    No Known Activations