© 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. 57007
    Prev
    Next
    INDEX
    Explanations

    technology and advanced systems

    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
    enne
    -0.08
    å¨Ħ
    -0.08
     Penis
    -0.08
     ÑĤеÑĢ
    -0.08
    姣
    -0.08
    coop
    -0.08
    æĭĻ
    -0.08
    ivité
    -0.08
    åĪ©äºļ
    -0.07
    æįŀ
    -0.07
    POSITIVE LOGITS
    çĭ¬æľīçļĦ
    0.11
    å·¥ä½ľæľºåĪ¶
    0.11
    çī¹æľīçļĦ
    0.10
     ÑĤеÑħнологии
    0.10
    设计çIJĨ念
    0.10
    çĭ¬å®¶
    0.10
    èĿĻ
    0.10
    âĦ¢
    0.10
     technology
    0.10
    çŃīå¤ļ项
    0.10
    Activations Density 0.109%

    No Known Activations