© 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. 37491
    Prev
    Next
    INDEX
    Explanations

    vaulted, vaults, vaulting

    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
    æ²Ĩ
    -0.10
    hood
    -0.09
    ual
    -0.09
    TOR
    -0.09
    ality
    -0.09
    aption
    -0.08
    讣
    -0.08
    æĦı大
    -0.08
    ç®
    -0.08
    ENTS
    -0.08
    POSITIVE LOGITS
    窿
    0.11
    iers
    0.11
    ing
    0.10
    bidden
    0.09
    ight
    0.09
    åĴĮåľ°åĮº
    0.09
    ehler
    0.09
    ulence
    0.08
    OrUpdate
    0.08
    yards
    0.08
    Activations Density 0.002%

    No Known Activations