© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51320
    Prev
    Next
    INDEX
    Explanations

    philosophy, philosophical, philosopher

    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
    çĦ¶æĺ¯
    -0.12
    èĭ´
    -0.09
    ãģĹãĤĩãģĨ
    -0.09
    EDA
    -0.08
    flow
    -0.08
    mund
    -0.08
    hem
    -0.08
    TING
    -0.08
    bies
    -0.08
    纶
    -0.08
    POSITIVE LOGITS
    letes
    0.10
    ä¸įçĦ¶
    0.10
    éĻ¢éķ¿
    0.09
    iller
    0.09
    otle
    0.09
     laure
    0.09
    /engine
    0.08
    cial
    0.08
    emu
    0.08
    LETE
    0.08
    Activations Density 0.013%

    No Known Activations