© 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. 56424
    Prev
    Next
    INDEX
    Explanations

    Iraq, Baghdad, hostage, security, spokesperson

    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
    åħļåĴĮåĽ½å®¶
    -0.10
    æĪ¿
    -0.10
    ertia
    -0.10
    éľ¹
    -0.09
    æıª
    -0.09
    RAFT
    -0.09
    ëł¹
    -0.09
    arer
    -0.08
    éĻ·
    -0.08
    é«»
    -0.08
    POSITIVE LOGITS
    汩
    0.09
    éĻĪè¿°
    0.09
    çļĦçĶ»éĿ¢
    0.09
    汨
    0.09
    éļıå¤Ħ
    0.09
    èĢĥçĤ¹
    0.09
    å½ĵåľ°çļĦ
    0.09
     dru
    0.09
    æķijæĬ¤è½¦
    0.09
    èĻŀ
    0.09
    Activations Density 0.177%

    No Known Activations