© 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. 2129
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    ÑĥниÑĨип
    -0.24
     (
    -0.23
    çŃīçŃī
    -0.22
    çŃīå¤ļç§į
    -0.22
     etc
    -0.22
    çŃīå·¥ä½ľ
    -0.21
    çŃīéĹ®é¢ĺ
    -0.21
    åĨįåĬłä¸Ĭ
    -0.21
     both
    -0.21
    (
    -0.21
    POSITIVE LOGITS
    byss
    0.24
    ();++
    0.24
    uraa
    0.24
    ⣵
    0.24
    Ÿ
    0.24
    /Branch
    0.23
    -mf
    0.23
    -Methods
    0.23
    ,");↵
    0.22
    благо
    0.22
    Activations Density 0.342%

    No Known Activations