© 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. 32252
    Prev
    Next
    INDEX
    Explanations

    mailto addresses and Gale/Gayle names

    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
    )NULL
    -0.09
    ãģı
    -0.09
    -Ta
    -0.09
    ignal
    -0.08
    çľļ
    -0.08
    ëħIJ
    -0.08
    _MEDIUM
    -0.08
     каÑĩ
    -0.08
    ENTE
    -0.08
    jac
    -0.08
    POSITIVE LOGITS
    ste
    0.09
    ·»
    0.09
    èľ¡
    0.09
    ä¸ĵ线
    0.09
    åĴ©
    0.09
    iolet
    0.09
    äºĨä¸Ģ声
    0.09
    ØŃØ©
    0.08
    çŀ½
    0.08
    éĺĤ
    0.08
    Activations Density 0.005%

    No Known Activations