© 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. 22934
    Prev
    Next
    INDEX
    Explanations

    doing so

    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
    è¿Ļäºĭ
    -0.10
    ÑĢа
    -0.10
    sic
    -0.10
    说åĪ°è¿ĻéĩĮ
    -0.09
    ä¿©
    -0.09
    æĿ¥è¯´
    -0.09
    åĪ°åľº
    -0.09
    nya
    -0.08
    说å®ŀè¯Ŀ
    -0.08
    åĭĥåĭĥ
    -0.08
    POSITIVE LOGITS
    /from
    0.11
     дела
    0.10
    æıĸ
    0.10
    ement
    0.10
    zech
    0.09
    reek
    0.09
    ayers
    0.09
    embers
    0.08
    ringe
    0.08
    вел
    0.08
    Activations Density 0.012%

    No Known Activations