© 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. 39015
    Prev
    Next
    INDEX
    Explanations

    joined others together

    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
    eneg
    -0.10
    acious
    -0.10
    åĬ£
    -0.09
    åĽº
    -0.09
    ä¾ĥ
    -0.09
     Manson
    -0.09
    gli
    -0.08
    æĸ§
    -0.08
    VICE
    -0.08
    æĢİä¹Īæł·
    -0.08
    POSITIVE LOGITS
    çľ¾
    0.09
     others
    0.09
    ä¼Ĺ
    0.09
    èµ
    0.09
    åĪ«äºº
    0.09
    akedown
    0.09
    ä¹ĥèĩ³
    0.08
    寻常
    0.08
    wor
    0.08
    ä¼ļ导èĩ´
    0.08
    Activations Density 0.016%

    No Known Activations