© 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. 11687
    Prev
    Next
    INDEX
    Explanations

    Venezuela

    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
    oste
    -0.09
    å®ģæ³¢
    -0.09
    PDO
    -0.09
    åĴ¥
    -0.08
     Warsaw
    -0.08
    WER
    -0.08
    èĦIJ
    -0.08
    плаÑĤ
    -0.08
    uber
    -0.08
    .il
    -0.08
    POSITIVE LOGITS
     Venezuel
    0.16
     venez
    0.12
    çĭ®
    0.10
     Venezuelan
    0.10
    omid
    0.10
    æµĶ
    0.09
    滹
    0.09
     Scot
    0.09
     Venezuela
    0.09
    çĶ¨åľ°
    0.09
    Activations Density 0.071%

    No Known Activations