© 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. 9003
    Prev
    Next
    INDEX
    Explanations

    distance or time measurements

    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
    ä½ľåĵģåĨħ容
    -0.09
    /s
    -0.09
    èħº
    -0.09
    åĪģ
    -0.08
    继
    -0.08
    温æ³ī
    -0.08
    çĥ¦èºģ
    -0.08
    ronic
    -0.08
     mam
    -0.08
    æĺĮ
    -0.08
    POSITIVE LOGITS
    ä¸įè¿ľ
    0.15
    åĩłæŃ¥
    0.13
    家éŨåı£
    0.11
    ä¸įè¿ľå¤Ħ
    0.11
    çīĩåĪ»
    0.11
    abble
    0.10
    è·Ŀ离
    0.10
    çļĦè·Ŀ离
    0.10
    away
    0.10
    ä¹ĭåĨħ
    0.10
    Activations Density 0.055%

    No Known Activations