© 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. 5899
    Prev
    Next
    INDEX
    Explanations

    broad applications or range

    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
    avel
    -0.09
    oretical
    -0.09
    çŁŃçŁŃ
    -0.09
    æĺİæĺ¾
    -0.08
    imiters
    -0.08
    CHR
    -0.08
    oft
    -0.08
    æ¦ľ
    -0.08
    aret
    -0.08
    ikh
    -0.08
    POSITIVE LOGITS
    å¹¿æ³ĽçļĦ
    0.10
    åħ±è¯Ĩ
    0.10
    èĢĮåĩº
    0.10
    laÅŁ
    0.09
    estr
    0.09
    cco
    0.09
    å¼ĢèĬ±
    0.09
    广
    0.09
    Łèĥ½
    0.09
    ially
    0.09
    Activations Density 0.028%

    No Known Activations