© 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. 61647
    Prev
    Next
    INDEX
    Explanations

    the followed by a place

    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
    æĦıä¹īä¸ĬçļĦ
    -0.11
    çĻ£
    -0.09
    hest
    -0.08
    åŃ£èĬĤ
    -0.08
    æµļ
    -0.08
    andin
    -0.08
    常å§Ķ
    -0.08
    ä¸Ģ家人
    -0.08
    åľ¨éĩĮéĿ¢
    -0.08
     ngá»į
    -0.08
    POSITIVE LOGITS
    äºĭåħĪ
    0.08
    éļĻ
    0.08
    å°±çŁ¥éģĵ
    0.08
    å¥ļ
    0.08
    uttle
    0.08
    è¾¹ä¸Ĭ
    0.08
    otes
    0.08
    lé
    0.08
    çijķ
    0.08
    ãĥĪãĥ¬
    0.08
    Activations Density 0.087%

    No Known Activations