© 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. 35608
    Prev
    Next
    INDEX
    Explanations

    measles or virus

    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
    ç«ĭãģ¦
    -0.10
    éĽĢ
    -0.10
    åħħ
    -0.09
    umb
    -0.09
    ãĤĥ
    -0.09
    èªĵ
    -0.09
    èµij
    -0.09
    è¯Ŀè¯Ń
    -0.09
    ä¸įæĸŃæıIJé«ĺ
    -0.08
     пед
    -0.08
    POSITIVE LOGITS
    çĭIJ
    0.10
    åı£è¢ĭ
    0.09
    ading
    0.09
    ç¦ħ
    0.09
     pup
    0.09
    åŁºæľ¬ä¸Ĭéĥ½
    0.09
    ä¸Ńéĵģ
    0.08
    çĿij
    0.08
    åįģåħ«å±Ĭ
    0.08
    åłĤ
    0.08
    Activations Density 0.031%

    No Known Activations