© 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. 49532
    Prev
    Next
    INDEX
    Explanations

    calendar andCabinet of image and fish in muscles like first two patient and

    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
     own
    -0.12
    /her
    -0.10
     favorite
    -0.10
     surroundings
    -0.10
    _favorite
    -0.10
     лÑİбим
    -0.09
    åĪ¹
    -0.09
    .Op
    -0.09
    è§Ĩ线
    -0.09
    ushi
    -0.09
    POSITIVE LOGITS
     seu
    0.16
     suo
    0.15
     sua
    0.15
    ä»ĸçļĦ
    0.15
    æĬĬèĩªå·±çļĦ
    0.14
    åħ¶
    0.14
     seus
    0.14
     suas
    0.13
    她çļĦ
    0.13
    对èĩªå·±çļĦ
    0.13
    Activations Density 0.674%

    No Known Activations