© 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. 699
    Prev
    Next
    INDEX
    Explanations

    political news report

    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
    linger
    -0.21
    -toggler
    -0.20
    illery
    -0.20
     cerco
    -0.20
    urate
    -0.20
    çŁ£
    -0.19
    positor
    -0.19
    "_
    -0.19
    OTOS
    -0.19
    "]){↵
    -0.19
    POSITIVE LOGITS
    ?"↵↵↵↵
    0.28
    :left
    0.25
    }elseif
    0.24
    åĽ¾ä¸º
    0.24
    (left
    0.23
    exampleInputEmail
    0.23
    chematic
    0.23
    å·¦
    0.22
    .opensource
    0.22
    åĪĨåĪ«ä¸º
    0.22
    Activations Density 0.757%

    No Known Activations