© 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. 20188
    Prev
    Next
    INDEX
    Explanations

    numbers and code snippets

    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
    çĶľèľľ
    -0.09
    cer
    -0.08
    çī¹æ®Ĭ
    -0.08
    çĶľ
    -0.08
    èĥľåĪ©
    -0.08
    è¿¢
    -0.08
    aram
    -0.08
    迹
    -0.07
    ney
    -0.07
    avar
    -0.07
    POSITIVE LOGITS
    eming
    0.10
    ç»Ĭ
    0.10
    ede
    0.09
    ROID
    0.09
     ì·¨
    0.09
    ÑĪка
    0.09
    éļıæīĭ
    0.09
    槿
    0.08
    æģĤ
    0.08
    ()._
    0.08
    Activations Density 0.074%

    No Known Activations