© 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. 29807
    Prev
    Next
    INDEX
    Explanations

    bystander, aring, peace, restaurants, asp, Oracle

    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
    urre
    -0.09
    ä¸Ģä½ĵåĮĸ
    -0.09
    å§Ķ
    -0.09
    å®ļäºĨ
    -0.08
    çļ¿
    -0.08
    Parallel
    -0.08
     alternate
    -0.08
    çıī
    -0.08
    eder
    -0.08
    对æĬĹ
    -0.08
    POSITIVE LOGITS
    ously
    0.10
    åĩºæīĭ
    0.10
    inker
    0.09
    ä¿ĥæĪIJ
    0.09
    angel
    0.09
     Corps
    0.09
    keit
    0.08
    鬼
    0.08
    iens
    0.08
    æ´ĭ
    0.08
    Activations Density 0.003%

    No Known Activations