© 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. 33790
    Prev
    Next
    INDEX
    Explanations

    regional cooperation, Pakistani Army, Indian Air Force

    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
    éļıæīĭ
    -0.10
    kek
    -0.09
    夫
    -0.09
    å¾ģ
    -0.09
    æ²®
    -0.09
    çĿ¢
    -0.09
    çĶĦ
    -0.09
    èĩ³å°Ĭ
    -0.08
     unavoid
    -0.08
    è¿Ľå±ķæĥħåĨµ
    -0.08
    POSITIVE LOGITS
    èģĶåĬ¨
    0.09
    Į¨
    0.09
    åĽ½åľŁ
    0.08
    éĺĦ
    0.08
    é«»
    0.08
    æıĴ
    0.08
    è¾¹å¢ĥ
    0.08
    åħ¬å®īæľºåħ³
    0.08
    etri
    0.08
    angement
    0.08
    Activations Density 0.126%

    No Known Activations