© 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. 35836
    Prev
    Next
    INDEX
    Explanations

    colors and brands

    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
    .Year
    -0.08
    íĥľ
    -0.08
     денÑĮ
    -0.08
    àºŃ
    -0.08
    нÑĮ
    -0.08
    ynos
    -0.08
     ÑģкаÑĩ
    -0.08
    orz
    -0.08
    æį
    -0.08
    _normalized
    -0.08
    POSITIVE LOGITS
    gence
    0.09
    å·¡åĽŀ
    0.09
    æĶ»åħ³
    0.09
    æ³ħ
    0.09
    æݨä»ĭ
    0.09
    oub
    0.09
    è·º
    0.08
    ä¸įæŃ»
    0.08
    客è¿IJ
    0.08
    å¸ĤåľºçĽij管
    0.08
    Activations Density 0.003%

    No Known Activations