© 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. 48897
    Prev
    Next
    INDEX
    Explanations

    volatile nature

    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
    iku
    -0.09
    bes
    -0.09
    dress
    -0.08
    dl
    -0.08
    dsa
    -0.08
    bir
    -0.08
    igraph
    -0.08
    ncmp
    -0.08
    _RESERVED
    -0.08
    igram
    -0.08
    POSITIVE LOGITS
    -minded
    0.10
    idad
    0.10
    æ¯Ļ
    0.10
    ãģ«ä¹Ĺ
    0.10
    ä¸Ģå¹ķ
    0.09
    ãģª
    0.09
    ä¸Ģéĺµ
    0.09
    ãģ«ãģĬ
    0.09
    te
    0.08
     minded
    0.08
    Activations Density 0.019%

    No Known Activations