© 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. 63375
    Prev
    Next
    INDEX
    Explanations

    forecasts and expectations

    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
    éļį
    -0.09
    æĭĴ
    -0.08
    åıijçİ°èĩªå·±
    -0.08
    ä¹ĭåŁİ
    -0.08
    idden
    -0.08
    NE
    -0.08
    ayo
    -0.07
    _gem
    -0.07
    幸è¿IJ
    -0.07
     NEC
    -0.07
    POSITIVE LOGITS
    åħ±è¯Ĩ
    0.17
     Expect
    0.14
    expect
    0.14
    ä¸Ģèĩ´
    0.13
     expect
    0.13
     consensus
    0.13
     expectations
    0.12
     expectation
    0.12
    æľŁå¾ħ
    0.12
    ä¸Ģèĩ´æĢ§
    0.12
    Activations Density 0.015%

    No Known Activations