© 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. 3638
    Prev
    Next
    INDEX
    Explanations

    set

    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
    ustralian
    -0.27
    urovision
    -0.26
    oplay
    -0.25
    ordion
    -0.24
    uckland
    -0.23
    Åķ
    -0.23
     cerco
    -0.23
     Polyester
    -0.22
    áº
    -0.21
    ulfilled
    -0.21
    POSITIVE LOGITS
    tlement
    0.31
    -Owned
    0.27
    /**<
    0.25
    éŃĶæ³ķå¸ĪåĴĮ
    0.25
    ONTAL
    0.24
    è¶Ĭä¾Ĩè¶Ĭ
    0.24
    }elseif
    0.24
    ////////////////////////////////////////////////////
    0.24
    _lastname
    0.24
    ////////////////////////////////////////////////////////////
    0.24
    Activations Density 0.136%

    No Known Activations