© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3981
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
    3
    -0.22
    ><?=$
    -0.20
    obia
    -0.19
    0
    -0.19
     dap
    -0.19
    è¿ĺåİŁ
    -0.19
    voke
    -0.19
    èijµ
    -0.18
    åı
    -0.18
    _chance
    -0.18
    POSITIVE LOGITS
    æĹłè®ºæĺ¯åħ¶
    0.29
    âļĹ
    0.26
     ×Ķ×ķ×ĵ
    0.26
    ependency
    0.24
     yarg
    0.24
    ëIJĺ기
    0.24
    ä¹łè¿ijå¹³æĢ»
    0.24
    )||(
    0.23
    CLAIM
    0.23
    âĴ¸
    0.23
    Activations Density 0.004%

    No Known Activations