© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4643
    Prev
    Next
    INDEX
    Explanations

    holy followed by a noun

    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
    强åĬĽ
    -0.10
    ingly
    -0.09
    alog
    -0.09
    olini
    -0.09
    ï¸ı
    -0.08
    SOR
    -0.08
    éĶ¦ç»£
    -0.08
    dre
    -0.08
    ä¸ĢåĪĨ
    -0.08
    .kotlin
    -0.08
    POSITIVE LOGITS
    ë¡Ń
    0.11
    ä»Ģä¹Īä¸ľè¥¿
    0.10
    åłĤ
    0.10
    å¸ľ
    0.09
    ensen
    0.09
    缼åħ¸
    0.09
    ائÙĤ
    0.09
    wort
    0.09
    ague
    0.09
     desk
    0.09
    Activations Density 0.015%

    No Known Activations