© 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. 56025
    Prev
    Next
    INDEX
    Explanations

    Zach, Zac, Zack

    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
    ived
    -0.09
    lijk
    -0.09
    IDER
    -0.08
    åIJĦæł·
    -0.08
    aru
    -0.08
    daÄŁ
    -0.08
    emple
    -0.08
    addle
    -0.08
    emble
    -0.08
    ÃŃvel
    -0.08
    POSITIVE LOGITS
    ìį¨
    0.10
    /her
    0.10
    é¦ĸåħĪè¦ģ
    0.10
    mers
    0.10
    ¤
    0.09
    arias
    0.09
    ìĦľ
    0.09
    âľį
    0.09
    IGN
    0.09
    istory
    0.09
    Activations Density 0.005%

    No Known Activations