© 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. 20410
    Prev
    Next
    INDEX
    Explanations

    car parts and features

    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
    uth
    -0.09
    èĴ¸
    -0.09
    èĴ¸æ±½
    -0.08
    æ¹ĸ
    -0.08
    è¶ģçĿĢ
    -0.08
    åİĤæĪ¿
    -0.08
    uling
    -0.08
    æ°Ķè¡Ģ
    -0.08
    çľ¼çĿĽ
    -0.08
    .axis
    -0.08
    POSITIVE LOGITS
    åIJķ
    0.10
    obox
    0.09
    åį§
    0.09
    æĭĤ
    0.09
    ris
    0.08
    çĪ±ç¾İ
    0.08
    æ²»
    0.08
    ILLS
    0.08
    anax
    0.08
    ROAD
    0.08
    Activations Density 0.079%

    No Known Activations