© 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. 51771
    Prev
    Next
    INDEX
    Explanations

    prior occurrences of numbers or abbreviations

    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
    åİŁåŀĭ
    -0.09
    æ²Ľ
    -0.09
    etime
    -0.09
    odos
    -0.09
    cie
    -0.08
    å¾Ĺå¤ļ
    -0.08
    ISC
    -0.08
    agers
    -0.08
    rado
    -0.08
    ãģ¾ãģ¾
    -0.08
    POSITIVE LOGITS
     Reputation
    0.10
    å¨ģåĬĽ
    0.09
    éļ¾
    0.09
    iens
    0.09
    preh
    0.08
    Occurred
    0.08
    ULLET
    0.08
    -cloud
    0.08
     reput
    0.08
    æį¢æĪIJ
    0.08
    Activations Density 0.227%

    No Known Activations