© 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. 8454
    Prev
    Next
    INDEX
    Explanations

    time indicators (am, pm)

    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
     tack
    -0.09
    éĻĶ
    -0.09
    squ
    -0.08
    楼主
    -0.08
    éģº
    -0.08
    éĿĽ
    -0.08
    rian
    -0.08
     пиÑĤаниÑı
    -0.08
    ivant
    -0.08
    annes
    -0.08
    POSITIVE LOGITS
    以ä¸ĬçļĦ
    0.10
     nons
    0.09
    è©Ī
    0.08
    å·¦åı³
    0.08
    -relative
    0.08
    åĹŁ
    0.08
     wiÄĻc
    0.08
    ìį¨
    0.08
    phen
    0.08
    æĿĵ
    0.08
    Activations Density 0.006%

    No Known Activations