© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37854
    Prev
    Next
    INDEX
    Explanations

    modelOR Meta, pyomo, consider vital, use Google, itative blood, model application

    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
    é£ĺ
    -0.10
    æ¼Ĥ
    -0.10
     PIO
    -0.09
    ä¸Ģåı£
    -0.09
    achs
    -0.09
     reck
    -0.09
    æį·
    -0.09
    åijµæĬ¤
    -0.09
    town
    -0.08
    é¢Ħ
    -0.08
    POSITIVE LOGITS
    åĨ³çŃĸ
    0.11
    RAM
    0.10
     Monte
    0.09
     Solver
    0.09
     decision
    0.09
    decision
    0.09
    FM
    0.09
    è¾¹éĻħ
    0.09
    æķ°åѦ
    0.09
    æı¿
    0.08
    Activations Density 0.062%

    No Known Activations