© 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. 3099
    Prev
    Next
    INDEX
    Explanations

    mathematical and technical

    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
    }elseif
    -0.22
    (*)(
    -0.21
     Raqqa
    -0.21
    urst
    -0.20
    _sv
    -0.19
    $/)
    -0.19
    è¿Ļä¸ªåľ°åĽ¾
    -0.18
    layui
    -0.18
    泡
    -0.18
    åĩ¤åĩ°ç½ij
    -0.18
    POSITIVE LOGITS
    warts
    0.24
    æī¾åĪ°
    0.23
    polator
    0.21
    á¾³
    0.21
    âĪĥ
    0.20
    æľīä¸Ģä½į
    0.20
    è½²
    0.20
    ailable
    0.20
    æī¾åĪ°äºĨ
    0.20
    eldon
    0.20
    Activations Density 0.055%

    No Known Activations