© 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. 7462
    Prev
    Next
    INDEX
    Explanations

    society

    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
    led
    -0.10
    onom
    -0.09
    eros
    -0.09
    èµĽåĮº
    -0.09
    iness
    -0.09
    imon
    -0.09
    æĪij们çİ°åľ¨
    -0.09
    istan
    -0.08
    çĿ«
    -0.08
    /right
    -0.08
    POSITIVE LOGITS
    -minded
    0.14
    eties
    0.12
    -wide
    0.11
    wide
    0.10
    hood
    0.10
    otch
    0.10
    ware
    0.10
    -facing
    0.09
    cloth
    0.09
    éļĪ
    0.09
    Activations Density 0.020%

    No Known Activations