© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51663
    Prev
    Next
    INDEX
    Explanations

    use of this

    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
    oku
    -0.10
    çIJĨäºĭ
    -0.09
    åĮĹæĸ¹
    -0.09
     ÙħÙĤ
    -0.08
    amac
    -0.08
     cust
    -0.08
    oma
    -0.08
    alm
    -0.08
    å¿µä½Ľ
    -0.08
    夯
    -0.08
    POSITIVE LOGITS
    çĶĺ
    0.10
     Cob
    0.10
    æĻºåºĵ
    0.09
    åĪĿæģĭ
    0.09
    =top
    0.09
    åѦçĶŁä»¬
    0.09
    èĬ³
    0.09
    Dock
    0.09
    /top
    0.09
    æ·
    0.09
    Activations Density 0.039%

    No Known Activations