© 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. 2173
    Prev
    Next
    INDEX
    Explanations

    required or mandatory

    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
    whereIn
    -0.23
    审æī¹
    -0.21
    æĢľ
    -0.20
    ä¸ĵä¸ļæĬĢæľ¯
    -0.19
    æģ¤
    -0.19
    æĿĥçĽĬ
    -0.19
    .writeValue
    -0.18
    åıijæĶ¾
    -0.18
    æ´½è°Ī
    -0.18
    æī¹å¤į
    -0.18
    POSITIVE LOGITS
    ä¹īåĬ¡
    0.44
     mandatory
    0.43
    强åĪ¶
    0.42
    mandatory
    0.40
     compulsory
    0.40
     obligations
    0.40
     obligation
    0.39
     Mandatory
    0.39
     Obl
    0.37
     obligatory
    0.36
    Activations Density 0.444%

    No Known Activations