© 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. 7155
    Prev
    Next
    INDEX
    Explanations

    its or their

    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
     dist
    -0.09
    çĶļèĩ³æĺ¯
    -0.08
    chal
    -0.08
    lash
    -0.08
    .shtml
    -0.08
    ÑĤÑĥÑĢ
    -0.08
     Hoy
    -0.08
    æĭĵ
    -0.08
    .pub
    -0.08
    lyn
    -0.08
    POSITIVE LOGITS
    åıĬåħ¶
    0.20
    åĴĮä»ĸçļĦ
    0.13
    æľ¬äºº
    0.12
     its
    0.11
    åħ¨å®¶
    0.11
    家å±ŀ
    0.11
    èĥĨ
    0.11
    éĻĦå±ŀ
    0.11
    åħ¨å¥Ĺ
    0.10
    ä¸Ģæ¢Ŀ
    0.10
    Activations Density 0.271%

    No Known Activations