© 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. 56056
    Prev
    Next
    INDEX
    Explanations

    oils and grease

    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
    EPS
    -0.09
    ote
    -0.09
    ight
    -0.09
    å¡Į
    -0.09
    èĵī
    -0.09
    avis
    -0.09
    æ¥Ķ
    -0.09
    æŃĩ
    -0.08
    _SUPPORT
    -0.08
    æĭĤ
    -0.08
    POSITIVE LOGITS
     oils
    0.11
    æ²¹èĦĤ
    0.10
    æīĭä¸Ĭ
    0.10
    å¯ĮåĬĽ
    0.09
    æı£
    0.09
    贪婪
    0.09
    éĽī
    0.09
    æ±Ĺæ°´
    0.09
    åĪĨè¡Į
    0.09
    æ²¹æ°Ķ
    0.09
    Activations Density 0.072%

    No Known Activations