© 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. 55385
    Prev
    Next
    INDEX
    Explanations

    crossroads and points

    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
    ãģıãģł
    -0.11
    å¸
    -0.10
    hood
    -0.10
    ẳ
    -0.09
    ä¸Ģçľ¼
    -0.09
    çļĦè·Ŀ离
    -0.09
    çĶŁäº§æĢ»åĢ¼
    -0.09
    blr
    -0.09
    peater
    -0.09
    éĻIJ度
    -0.09
    POSITIVE LOGITS
    icts
    0.08
    çİ°åĩº
    0.08
    nod
    0.08
    ãĥŀãĥ¼
    0.08
     Gregg
    0.08
    ides
    0.08
    Gab
    0.08
    «
    0.08
    ocos
    0.08
     tow
    0.08
    Activations Density 0.005%

    No Known Activations