© 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. 39556
    Prev
    Next
    INDEX
    Explanations

    latest version

    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
    nton
    -0.10
    åĥĸ
    -0.10
    PELL
    -0.10
    ä¹ĭæĺŁ
    -0.09
    ä¸¥æł¼
    -0.09
    ikit
    -0.09
    泺
    -0.09
    è´©
    -0.09
    åķ¾
    -0.09
    overe
    -0.08
    POSITIVE LOGITS
    æľĢæĸ°
    0.10
    çħ
    0.09
    ergy
    0.09
    æľĢæĸ°çļĦ
    0.09
    å°½åı¯èĥ½
    0.09
    é²ľ
    0.09
    ç¼ij
    0.08
    éĺ²å¾¡
    0.08
    hm
    0.08
    quarter
    0.08
    Activations Density 0.065%

    No Known Activations