© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37736
    Prev
    Next
    INDEX
    Explanations

    coding=utf-8

    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
    rail
    -0.09
    Ø·ÙĬ
    -0.08
    说çĿĢ
    -0.08
    åı·ç§°
    -0.08
     Ñģобой
    -0.08
    æ±½
    -0.08
    åĪ°ä½į
    -0.08
    паÑĢ
    -0.08
    udio
    -0.08
    ili
    -0.08
    POSITIVE LOGITS
    letes
    0.11
    è§īæĤŁ
    0.09
    éĻĽä¸ĭ
    0.09
    çĥĺ
    0.09
    ince
    0.09
    å¾Ģäºĭ
    0.09
    _SERIAL
    0.09
    croft
    0.08
    lav
    0.08
    æĽĻåħī
    0.08
    Activations Density 0.003%

    No Known Activations