© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48599
    Prev
    Next
    INDEX
    Explanations

    th followed by word beginnings

    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
    -0.10
    ision
    -0.10
    ONENT
    -0.10
    ع
    -0.09
    	TokenName
    -0.09
    urator
    -0.09
    滩
    -0.09
     Braun
    -0.09
    idence
    -0.09
    -minded
    -0.09
    POSITIVE LOGITS
    ãģ£ãģįãĤĬ
    0.13
    ousands
    0.12
    ened
    0.12
    ursday
    0.12
    /th
    0.11
    ilde
    0.10
    ogh
    0.10
    rottle
    0.10
    alers
    0.10
    omas
    0.10
    Activations Density 0.109%

    No Known Activations