© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52794
    Prev
    Next
    INDEX
    Explanations

    alumni and former students

    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
    è¿Īè¿Ľ
    -0.10
    æĪij们å¿ħé¡»
    -0.09
    .githubusercontent
    -0.09
    æĸ°å½¢åĬ¿
    -0.09
    å³»
    -0.09
    ening
    -0.09
    atives
    -0.09
    åīįè¿Ľ
    -0.09
    cloth
    -0.09
    æĬ¹
    -0.09
    POSITIVE LOGITS
    apos
    0.10
    åĪ¶åº¦æĶ¹éĿ©
    0.09
    yard
    0.09
    aug
    0.09
    yards
    0.09
    IDD
    0.09
    涯
    0.09
    stration
    0.09
    å¨ĺ
    0.09
    ship
    0.09
    Activations Density 0.005%

    No Known Activations