© 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. 3229
    Prev
    Next
    INDEX
    Explanations

    moreover, furthermore

    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
    licted
    -0.27
    oggler
    -0.26
    ombine
    -0.23
    stantiate
    -0.22
     ãĥĪãĥ©ãĥĥãĤ¯
    -0.22
    ;;;;;;;;;;;;;;;;
    -0.22
    ubre
    -0.21
    alleries
    -0.21
    undos
    -0.21
    quisitions
    -0.21
    POSITIVE LOGITS
     cocks
    0.21
     stag
    0.20
     esl
    0.20
    å¾Ĺ天çĭ¬åİļ
    0.20
     ermög
    0.20
    åıijå±ķæł¼å±Ģ
    0.19
     intimid
    0.19
    èĥĸåŃIJ
    0.19
    ä¸Ķ
    0.18
    åĺ£
    0.18
    Activations Density 0.084%

    No Known Activations