© 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. 17207
    Prev
    Next
    INDEX
    Explanations

    places and names

    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
    碣
    -0.09
    åħ¨æĿij
    -0.09
    Īëĭ¤
    -0.08
    讼
    -0.08
    æĸĭ
    -0.08
    oftware
    -0.08
    åħ¥éŨ
    -0.08
    缴è¨Ģ
    -0.08
    æ²³åĮĹ
    -0.08
    ìĹ¼
    -0.08
    POSITIVE LOGITS
    åĵ¨
    0.11
    èĪIJ
    0.10
    ç§ģç«ĭ
    0.09
    ANEL
    0.09
    anyl
    0.09
    对æĪij
    0.09
    .contents
    0.09
    ä¸Ńå¿ĥåŁİåĮº
    0.09
    åĢŁçĶ¨
    0.08
    ycz
    0.08
    Activations Density 0.139%

    No Known Activations