© 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. 32800
    Prev
    Next
    INDEX
    Explanations

    java ArrayList

    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
    edImage
    -0.12
    åħ¥ãĤĮ
    -0.10
    gart
    -0.10
    ä»Ģä¹Īéĥ½
    -0.09
    缴è¾ĸ
    -0.09
    å¡ĺ
    -0.09
    头çĸ¼
    -0.09
    ilm
    -0.09
    NING
    -0.09
    CKER
    -0.09
    POSITIVE LOGITS
    ä¸įå¼Ģ
    0.11
    iska
    0.10
    uit
    0.09
    涪
    0.09
    åı¯è¡ĮæĢ§
    0.09
    ienne
    0.08
    alytics
    0.08
    bers
    0.08
    å¿ĥæĥħ
    0.08
    /on
    0.08
    Activations Density 0.007%

    No Known Activations