© 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. 2672
    Prev
    Next
    INDEX
    Explanations

    start and starting

    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
    è´¯éĢļ
    -0.10
    åĭī
    -0.10
    çªĹå¤ĸ
    -0.09
    andin
    -0.09
    æķij人
    -0.09
    æ½ĩ
    -0.09
    _KIND
    -0.09
    Ùħد
    -0.09
    omes
    -0.09
    åĽłæŀľ
    -0.09
    POSITIVE LOGITS
    èµ·çĤ¹
    0.11
    Start
    0.10
    	Start
    0.09
    å¼ĢçĽĺ
    0.09
    _start
    0.09
    ãĤ¹ãĤ¿ãĥ¼ãĥĪ
    0.09
    èį·
    0.09
    start
    0.09
    è¸ıä¸Ĭ
    0.09
    åıĤåĬł
    0.09
    Activations Density 0.067%

    No Known Activations