© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 818
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
    èħ§
    -0.25
    /on
    -0.20
     berlin
    -0.19
    .jface
    -0.19
    注æĺİåĩºå¤Ħ
    -0.19
    ÑĤели
    -0.19
     Proud
    -0.18
     inkl
    -0.18
    typings
    -0.18
    wa
    -0.18
    POSITIVE LOGITS
    HTTPRequest
    0.24
    =".$_
    0.23
    å£ħ
    0.23
    :result
    0.22
    ITO
    0.22
    -opacity
    0.21
    /pi
    0.21
    ompiler
    0.21
    ancock
    0.21
    çu
    0.20
    Activations Density 0.021%

    No Known Activations