© 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. 3615
    Prev
    Next
    INDEX
    Explanations

    code and technical 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
    :[[
    -0.26
    IOC
    -0.24
    ioneer
    -0.21
    subpackage
    -0.21
    éĶĺ
    -0.21
    akens
    -0.21
    ;break
    -0.20
    olvers
    -0.20
    uida
    -0.20
    æ®ĸ
    -0.20
    POSITIVE LOGITS
    ÑĥпиÑĤÑĮ
    0.21
    å¤©åľ°
    0.21
    stateParams
    0.21
    PLEMENT
    0.19
    _fatal
    0.19
     kako
    0.19
    gest
    0.18
    æŃ£æĸĩ
    0.18
    RelativeTo
    0.18
    æ»Ķ
    0.18
    Activations Density 0.002%

    No Known Activations