© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10009
    Prev
    Next
    INDEX
    Explanations

    write a

    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
    åIJĪä½ľåħ±èµ¢
    -0.10
    images
    -0.08
    ç°¿
    -0.08
    è¾ľè´Ł
    -0.08
    ction
    -0.08
    æ°ij
    -0.08
    æŀ¯
    -0.08
    аÑĤÑĥÑĢ
    -0.08
    otor
    -0.08
    Editors
    -0.08
    POSITIVE LOGITS
    ocos
    0.10
     Darkness
    0.09
    ä¸Ģåıªæīĭ
    0.09
    åľ¨éĤ£éĩĮ
    0.09
    è¿Ļæĺ¯åĽłä¸º
    0.08
     Parish
    0.08
    á»ķi
    0.08
    åłĤ
    0.08
    èħĭ
    0.08
    åij
    0.08
    Activations Density 0.003%

    No Known Activations