© 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. 48344
    Prev
    Next
    INDEX
    Explanations

    continue or follow

    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
    驹
    -0.10
    纽
    -0.09
    çĤ¹äºĨ
    -0.09
    åĢı
    -0.09
    æįŀ
    -0.09
     Ced
    -0.09
    á»ģn
    -0.09
    å£ħ
    -0.08
    å®Īä½ı
    -0.08
    çĶŁäº§å·¥èīº
    -0.08
    POSITIVE LOGITS
    emark
    0.08
    oped
    0.08
     sopr
    0.08
    몽
    0.08
    ä¸Ģ段
    0.08
    缴åĪ°
    0.08
    éĴī
    0.08
    ORS
    0.08
    æľĢ主è¦ģ
    0.08
    ä¸Ģ缴åĪ°
    0.08
    Activations Density 0.035%

    No Known Activations