© 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. 36816
    Prev
    Next
    INDEX
    Explanations

    behind the door

    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
    æ¯Ķäºļ
    -0.09
    夤
    -0.08
    ÑĪин
    -0.08
    ¦
    -0.08
     confront
    -0.08
    alli
    -0.08
    thon
    -0.08
    eri
    -0.08
    æĬĬæı¡
    -0.07
    /=
    -0.07
    POSITIVE LOGITS
     Ñģобой
    0.14
    door
    0.12
    wards
    0.11
     него
    0.11
    WARDS
    0.11
    ward
    0.10
    ages
    0.10
    çļĦæŶéĹ´éĩĮ
    0.10
    aler
    0.10
    doors
    0.09
    Activations Density 0.017%

    No Known Activations