© 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. 26718
    Prev
    Next
    INDEX
    Explanations

    motion sickness or photo

    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
    OrUpdate
    -0.11
    hold
    -0.11
    æ¯ĽåŃĶ
    -0.09
    бÑĭ
    -0.09
    uil
    -0.09
    æĭĹ
    -0.09
    alto
    -0.09
    ÑĪе
    -0.09
    åĨ¶
    -0.09
    åĬłå¿«å»ºè®¾
    -0.09
    POSITIVE LOGITS
    ìį¨
    0.11
    oso
    0.09
    alem
    0.09
    preter
    0.09
    ally
    0.09
    oring
    0.08
    nant
    0.08
     sickness
    0.08
    less
    0.08
    -motion
    0.08
    Activations Density 0.032%

    No Known Activations