© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51508
    Prev
    Next
    INDEX
    Explanations

    iPhone models and versions

    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
    缴åįĩ
    -0.11
    è··
    -0.10
    \application
    -0.10
    豪éŨ
    -0.09
    ä¹ĭæĺŁ
    -0.09
    æĭīåįĩ
    -0.09
    éĢĥèĦ±
    -0.09
    åĵ¡
    -0.09
    æĺŃ
    -0.08
    æĪIJåĬŁçļĦ
    -0.08
    POSITIVE LOGITS
    èĮ§
    0.09
    为æĬĵ
    0.09
    ERR
    0.08
     gamb
    0.08
    ICS
    0.08
    ä¹łæĥ¯
    0.08
     sæ
    0.08
    áµī
    0.08
    éĵ¸
    0.08
     cầm
    0.08
    Activations Density 0.013%

    No Known Activations