© 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. 28031
    Prev
    Next
    INDEX
    Explanations

    words starting with z

    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
    éĻIJãĤĬ
    -0.09
    é³Į
    -0.09
     FOOT
    -0.08
    ennis
    -0.08
    sek
    -0.08
     Noble
    -0.08
    çŃĨ
    -0.08
    umes
    -0.08
     «
    -0.08
    æ·±æĥħ
    -0.08
    POSITIVE LOGITS
    ebra
    0.11
    edException
    0.10
    交ä¼ļ
    0.10
    *dt
    0.09
    elter
    0.09
     quot
    0.08
    æĸĹ
    0.08
    ä½ļ
    0.08
    åħ¨åĽ½
    0.08
     sideline
    0.08
    Activations Density 0.031%

    No Known Activations