© 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. 2623
    Prev
    Next
    INDEX
    Explanations

    S

    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
    ;br
    -0.29
    ofilm
    -0.24
    .Does
    -0.24
    -Sah
    -0.24
    FormsModule
    -0.23
    ylko
    -0.23
    *pow
    -0.23
    Slf
    -0.23
    ilon
    -0.23
    rippling
    -0.22
    POSITIVE LOGITS
    æīĥ
    0.21
    ãİı
    0.21
     osp
    0.20
    大家éĥ½
    0.20
     newPos
    0.20
    -lo
    0.19
    çĪ±
    0.19
    netinet
    0.19
    åĴĶ
    0.18
     Monterey
    0.18
    Activations Density 0.005%

    No Known Activations