© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1710
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    并ä¸įæĺ¯å¾Ī
    -0.30
    @Configuration
    -0.23
    èĸľ
    -0.22
    å¸ij
    -0.22
    å¾Īä¸įéĶĻ
    -0.22
     LoginActivity
    -0.20
    ä¹Łä¸įéĶĻ
    -0.20
    @Path
    -0.20
    getHeight
    -0.20
    éĥ½æĺ¯éĿŀ常
    -0.20
    POSITIVE LOGITS
     ($('#
    0.26
     ($("#
    0.26
    ifestyles
    0.25
    :<?
    0.25
    ActivityResult
    0.23
     pornstar
    0.22
    ĵĺ
    0.22
    âĸ¿
    0.22
    -With
    0.21
    VEL
    0.21
    Activations Density 0.579%

    No Known Activations