© 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. 3153
    Prev
    Next
    INDEX
    Explanations

    sort/type

    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
    iren
    -0.24
    ','');↵
    -0.22
    沪æĮĩ
    -0.21
    äºĨåįĬ天
    -0.21
    aceut
    -0.21
     (!((
    -0.20
    PasswordEncoder
    -0.20
    ãģĤãĤĬãģĮãģ¨ãģĨãģĶãģĸ
    -0.20
    ',...↵
    -0.20
    .fm
    -0.20
    POSITIVE LOGITS
     ilk
    0.34
     sort
    0.25
     magnitude
    0.24
     persuasion
    0.22
    magnitude
    0.22
     kind
    0.22
    -kind
    0.22
    å¹´ä¸ĭåįĬå¹´
    0.21
    Magnitude
    0.21
     type
    0.21
    Activations Density 0.775%

    No Known Activations