© 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. 7718
    Prev
    Next
    INDEX
    Explanations

    guest or attendee status

    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
    é©°
    -0.10
    æĪ¢
    -0.10
    undi
    -0.09
    ick
    -0.09
    ohl
    -0.08
    缴è¨Ģ
    -0.08
    _subscribe
    -0.08
    AndView
    -0.08
    认è¯Ĩ
    -0.08
    idable
    -0.08
    POSITIVE LOGITS
    .ibm
    0.09
    ÙģØŃ
    0.09
    apo
    0.09
    WARE
    0.08
    joined
    0.08
    éĢ¸
    0.08
    ellan
    0.08
    /cop
    0.08
    æ±Ģ
    0.08
    ê°Ŀ
    0.08
    Activations Density 0.068%

    No Known Activations