© 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. 8086
    Prev
    Next
    INDEX
    Explanations

    rev/REV variations and suffixes

    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
    Ñīик
    -0.08
    ä¼ļåIJĮ
    -0.08
    chos
    -0.08
    erializer
    -0.08
    retval
    -0.08
    åŃ¦å®¶
    -0.07
    éĩįéĩį
    -0.07
     Exped
    -0.07
    UM
    -0.07
    hip
    -0.07
    POSITIVE LOGITS
    aries
    0.13
    è¿ĩæĿ¥
    0.13
    éģİä¾Ĩ
    0.11
    .rev
    0.10
    OLE
    0.10
    uster
    0.10
    ISED
    0.10
    äºĨè¿ĩæĿ¥
    0.10
    okable
    0.10
    å°¼äºļ
    0.10
    Activations Density 0.028%

    No Known Activations