© 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. 22482
    Prev
    Next
    INDEX
    Explanations

    Sioux Tribe or similar 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
    ts
    -0.09
    nea
    -0.09
    鲧
    -0.09
    éĬ·
    -0.08
    osl
    -0.08
    ä¸įèĤ¯
    -0.08
    à°¬
    -0.08
    phans
    -0.08
    айн
    -0.08
    çĵ®
    -0.08
    POSITIVE LOGITS
    éĢĬ
    0.10
    éĺĶ
    0.10
    spr
    0.09
    åı¨
    0.09
    èĮ¹
    0.09
    èĥ½æĬĬ
    0.09
     rdr
    0.09
    inv
    0.09
    è±¹
    0.09
    kee
    0.09
    Activations Density 0.001%

    No Known Activations