© 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. 31889
    Prev
    Next
    INDEX
    Explanations

    Panama and Panamanian

    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
    ful
    -0.14
    fully
    -0.12
    fulness
    -0.10
    ness
    -0.10
    enance
    -0.10
    esign
    -0.10
    sWith
    -0.09
    FUL
    -0.09
    褰
    -0.09
     Lowell
    -0.08
    POSITIVE LOGITS
    ikal
    0.11
    ectors
    0.10
    请æĤ¨
    0.10
    ously
    0.09
     webcam
    0.08
    èijŃ
    0.08
    黩
    0.08
    ê¹Ģ
    0.08
    幡
    0.08
    ties
    0.08
    Activations Density 0.007%

    No Known Activations