© 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. 11080
    Prev
    Next
    INDEX
    Explanations

    cables, tubing, and wires

    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¤IJåİħ
    -0.09
    éªijåħµ
    -0.09
    pk
    -0.08
    åĮºç®¡å§Ķä¼ļ
    -0.08
     Duffy
    -0.08
    çľ¼è§Ĵ
    -0.08
    广æĴŃ
    -0.08
    女åŃ©
    -0.08
     Pall
    -0.08
     Vick
    -0.08
    POSITIVE LOGITS
    å¾Īéķ¿
    0.11
    延éķ¿
    0.09
     trần
    0.09
    Bundle
    0.09
     lengths
    0.08
    _globals
    0.08
    带çĿĢ
    0.08
    ä¸Ģæł¹
    0.08
    ä¸Ģ段
    0.08
    uti
    0.08
    Activations Density 0.138%

    No Known Activations