© 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. 3127
    Prev
    Next
    INDEX
    Explanations

    code related text

    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
     yarg
    -0.25
     "','
    -0.22
     */↵↵↵↵
    -0.20
    vu
    -0.19
    以人æ°ij为
    -0.19
    æĹłè®ºæĺ¯åħ¶
    -0.19
    éĺĩ
    -0.19
     положиÑĤелÑĮн
    -0.19
     tatto
    -0.19
     [-]:
    -0.18
    POSITIVE LOGITS
    łģ
    0.19
    縻
    0.18
     writeTo
    0.18
    -cols
    0.18
    ibold
    0.18
    andin
    0.18
    clerosis
    0.18
    jem
    0.18
    ($('
    0.18
    .Desc
    0.18
    Activations Density 0.002%

    No Known Activations