© 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. 39592
    Prev
    Next
    INDEX
    Explanations

    elevation and land levels

    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
    åŁ
    -0.09
    æ·ĭ
    -0.09
    è¦Ĩ
    -0.09
     fixed
    -0.09
    åĪĨæĺİ
    -0.08
    çŁ¿çī©
    -0.08
    å¢ĥåĨħ
    -0.08
    ilen
    -0.08
    åŃĹæł·
    -0.08
    iller
    -0.08
    POSITIVE LOGITS
     violet
    0.09
    igu
    0.09
    ä¸Ĭ涨
    0.09
    æ¸İ
    0.09
    enas
    0.09
    海岸
    0.09
    riers
    0.09
    åŃļ
    0.08
    ateral
    0.08
    еÑģÑĤ
    0.08
    Activations Density 0.016%

    No Known Activations