© 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. 17577
    Prev
    Next
    INDEX
    Explanations

    names of newspapers

    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
    åĮĹ京å¸Ĥ
    -0.10
    º
    -0.09
    asi
    -0.09
    ablish
    -0.08
    kip
    -0.08
    ights
    -0.08
    atu
    -0.08
    åħĪè¡Į
    -0.08
    æ½ŀ
    -0.08
    çĽ´è¾¾
    -0.08
    POSITIVE LOGITS
    ç»ıæµİæĬĢæľ¯
    0.10
    äºĮæīĭæĪ¿
    0.09
    kowski
    0.09
    åľ¨åĽ½åĨħ
    0.09
    å£ħ
    0.09
    è¿Ļå¼ł
    0.09
    çĭĥ
    0.09
    æĭ¢
    0.09
    åĴ¸éĺ³
    0.09
    éĢģåĩº
    0.09
    Activations Density 0.014%

    No Known Activations