© 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. 35058
    Prev
    Next
    INDEX
    Explanations

    fuel injection systems

    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
    æİ¢
    -0.10
    æ¤Ĵ
    -0.10
    çĥŁçģ«
    -0.09
    umpy
    -0.08
    侯
    -0.08
     waive
    -0.08
    sert
    -0.08
    å°ıæŶåĢĻ
    -0.08
    缺
    -0.08
    ruc
    -0.08
    POSITIVE LOGITS
    utor
    0.09
    åģĥ
    0.09
    kick
    0.09
    éħįéĢģ
    0.09
    .Toggle
    0.09
    æĶ¹ä¸º
    0.09
    æĶ»åĿļ
    0.08
    缮åīįåĽ½åĨħ
    0.08
     Walnut
    0.08
     AuthenticationService
    0.08
    Activations Density 0.078%

    No Known Activations