© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 37105
    Prev
    Next
    INDEX
    Explanations

    characters in stories

    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
    orst
    -0.09
    èĢģ人家
    -0.09
    stile
    -0.09
    anden
    -0.09
    yer
    -0.09
    burgh
    -0.09
    æłĭ
    -0.08
    ocity
    -0.08
    æ·¹
    -0.08
    æł·çļĦ
    -0.08
    POSITIVE LOGITS
    akter
    0.09
    IBUT
    0.09
    elib
    0.08
    tered
    0.08
    ä¼Ĺå¤ļ
    0.08
    é²ľæĺİ
    0.08
    enate
    0.08
     öde
    0.08
    çĻ»
    0.08
    为äºĨæĽ´å¥½
    0.08
    Activations Density 0.018%

    No Known Activations