© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 227
    Prev
    Next
    INDEX
    Explanations

    male fertility control

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    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
     vidé
    -0.35
    åĵĪåĵĪåĵĪåĵĪ
    -0.31
     véhic
    -0.31
    ÑģÑĤолÑĮ
    -0.29
    تÙĦÙĥ
    -0.28
    تضÙħÙĨ
    -0.28
    æĤ»
    -0.28
     ApplicationException
    -0.27
    BASEPATH
    -0.26
     cosplay
    -0.26
    POSITIVE LOGITS
     èĩªåĬ¨çĶŁæĪIJ
    0.31
    AndHashCode
    0.31
     tats
    0.31
    alborg
    0.31
    URLException
    0.30
    úsqueda
    0.29
     Dortmund
    0.29
    visor
    0.29
    >'.↵
    0.28
    :'.$
    0.28
    Activations Density 11.251%

    No Known Activations