© 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. 3141
    Prev
    Next
    INDEX
    Explanations

    .

    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
    ãĥĭãĥĥãĤ¯
    -0.19
     Donne
    -0.18
     objectMapper
    -0.18
    åģ¶
    -0.18
     IService
    -0.18
    ç½ijå°ıç¼ĸ
    -0.18
    çĻ¾åĪĨçĻ¾
    -0.18
    forcements
    -0.18
    setError
    -0.17
    ëĭ¤ê°Ģ
    -0.17
    POSITIVE LOGITS
    å¹³åĿĩ
    0.43
     average
    0.39
     averaging
    0.34
    average
    0.34
     Average
    0.33
    å¹³åĿĩæ°´å¹³
    0.32
     averaged
    0.32
    Average
    0.31
     averages
    0.31
    -average
    0.27
    Activations Density 0.129%

    No Known Activations