© 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. 9466
    Prev
    Next
    INDEX
    Explanations

    titles and descriptive phrases

    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
    æľīç§į
    -0.11
    éĤ£ç§į
    -0.10
    廪
    -0.10
    缴
    -0.10
    æĮĪ
    -0.09
    å°º
    -0.09
     sourceMapping
    -0.09
    _ABI
    -0.09
    è¿ĻäºĽå¹´
    -0.09
    ä¹Łæ¯Ķè¾ĥ
    -0.09
    POSITIVE LOGITS
    ä¹ĭ称
    0.09
    ä¸įåħĭä¸įåıĬ
    0.08
     Glad
    0.08
    ses
    0.08
    èĬĻ
    0.08
    读æĩĤ
    0.08
    çŃīåĨħ容
    0.08
    éļıæŶéļıåľ°
    0.08
    åĨł
    0.08
    ä¸įæĥ³
    0.08
    Activations Density 0.091%

    No Known Activations