© 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. 305
    Prev
    Next
    INDEX
    Explanations

    technical code terms

    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
    u
    -0.25
    Ñģложн
    -0.24
    ed
    -0.24
    suming
    -0.22
    æŃ¤é¡¹
    -0.21
     dildo
    -0.21
     setAddress
    -0.21
    o
    -0.21
     membr
    -0.20
    ä¿Ĺè¯Ŀ说
    -0.20
    POSITIVE LOGITS
    rippling
    0.33
    ihanna
    0.30
    ..'
    0.29
     ÑģенÑĤ
    0.28
    __$
    0.28
    ðŁĺī
    0.27
     (!((
    0.27
    BOSE
    0.27
    chedulers
    0.27
     misunder
    0.26
    Activations Density 14.517%

    No Known Activations