© 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. 18180
    Prev
    Next
    INDEX
    Explanations

    County, Hospital, Superior Court

    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
    åıĶ
    -0.09
    izza
    -0.08
    éĥ½éĿŀ常
    -0.08
     Wall
    -0.08
    ä¸į便
    -0.08
    uka
    -0.08
    åŀĤ
    -0.08
    нев
    -0.08
    ucc
    -0.08
    yan
    -0.08
    POSITIVE LOGITS
    éķ¿èĢģ
    0.10
    æłĬ
    0.10
    æѧ
    0.10
    ä¸Ńå¤ĸ
    0.10
    å·¥ä¸ļ大åѦ
    0.10
    tran
    0.10
    ableView
    0.09
    æ´²
    0.09
    å²IJ
    0.09
    .scheme
    0.09
    Activations Density 0.007%

    No Known Activations