© 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. 18989
    Prev
    Next
    INDEX
    Explanations

    bleaching, blanched, aching

    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
    eltas
    -0.13
    shaw
    -0.12
    累累
    -0.10
    nodoc
    -0.10
    licative
    -0.10
    åĪĩåħ¥
    -0.09
     najczÄĻÅĽciej
    -0.09
    深深
    -0.09
    lius
    -0.09
    lijk
    -0.09
    POSITIVE LOGITS
    holder
    0.09
    æĻ°
    0.09
    åīĤ
    0.08
    rig
    0.08
    ening
    0.08
    ç½²
    0.08
    eners
    0.08
    ened
    0.07
    æī«ä¸Ģ
    0.07
    èģĴ
    0.07
    Activations Density 0.011%

    No Known Activations