© 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. 56539
    Prev
    Next
    INDEX
    Explanations

    Newtonnewts

    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
    ucker
    -0.10
    wahl
    -0.10
    å¼ĥ
    -0.10
    icer
    -0.09
    çĶ°éĩİ
    -0.09
    ioneer
    -0.09
    à¸İ
    -0.09
    .OnClickListener
    -0.08
    ç²Ĺç³Ļ
    -0.08
    ä¹ŀ
    -0.08
    POSITIVE LOGITS
    ie
    0.10
    OL
    0.08
     ngữ
    0.08
    乡
    0.08
    osit
    0.08
    Υ
    0.08
    izr
    0.08
    çĬĩ
    0.08
    midd
    0.08
    åĬŀæ³ķ
    0.08
    Activations Density 0.007%

    No Known Activations