© 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. 2402
    Prev
    Next
    INDEX
    Explanations

    click here

    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
    |min
    -0.26
    åĽ½éĻħåľ¨çº¿
    -0.26
    |int
    -0.23
    ');");↵
    -0.22
    ("'"
    -0.22
    ")));
    -0.21
    |required
    -0.20
     khoá
    -0.20
    @update
    -0.20
    >');
    -0.20
    POSITIVE LOGITS
    äºĨ好å¤ļ
    0.23
    第äºĮèĬĤ
    0.22
    опÑĢеделен
    0.20
    è®Ģåıĸ
    0.20
    .BLL
    0.20
     bian
    0.19
     Sized
    0.19
     Shortcut
    0.18
    á¼Ħ
    0.18
     consc
    0.18
    Activations Density 0.002%

    No Known Activations