© 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. 10176
    Prev
    Next
    INDEX
    Explanations

    Mohamed, Abdul, Mohammad, Hassan

    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
    åīįèĢħ
    -0.08
    åīįéĿ¢
    -0.08
    éĥı
    -0.08
     củ
    -0.08
    idge
    -0.08
    åīį端
    -0.08
     reinst
    -0.08
    çŃīå½¢å¼ı
    -0.08
    istr
    -0.08
    åı¸
    -0.08
    POSITIVE LOGITS
    ç²¾çĽĬæ±Ĥç²¾
    0.10
     пÑĢиÑĩ
    0.09
    dess
    0.09
    éªĪ
    0.09
     Wich
    0.09
    iens
    0.09
    å¹ķåIJİ
    0.08
    ä½ľèĢħæľ¬äºº
    0.08
    ä¸īåįĥ
    0.08
    ç§Ģ
    0.08
    Activations Density 0.098%

    No Known Activations