© 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. 3630
    Prev
    Next
    INDEX
    Explanations

    duration of treatment

    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
    å½ĵåľº
    -0.09
    é«ĺéĢŁ
    -0.09
    enumer
    -0.09
    çŀ¬éĹ´
    -0.09
    éĤ£ä¸ĢåĪ»
    -0.08
    å·¡
    -0.08
    游ä¹IJ
    -0.08
    Coefficient
    -0.08
    羡
    -0.08
    设计çIJĨ念
    -0.08
    POSITIVE LOGITS
    è§ģæķĪ
    0.12
    çĶ¨äºĨ
    0.11
     discontin
    0.10
    ä¸Ģ段æŶéĹ´
    0.10
    ä¹°äºĨ
    0.09
    使çĶ¨
    0.09
    ç¶ļãģij
    0.09
    æķĪæŀľ
    0.09
    çĶ¨éĩı
    0.09
    滥çĶ¨
    0.09
    Activations Density 0.262%

    No Known Activations