© 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. 3485
    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
     ++;↵
    -0.24
     *</
    -0.22
    č↵		č↵
    -0.22
    :';↵
    -0.21
    _globals
    -0.21
    obao
    -0.21
    ++;č↵č↵
    -0.21
    orpor
    -0.20
    ROTO
    -0.20
    ,No
    -0.20
    POSITIVE LOGITS
     overd
    0.22
     threesome
    0.22
    éĩįè¦ģåİŁåĽł
    0.21
    olicitud
    0.21
    åĴ¸
    0.21
    xFFFFFF
    0.20
     brid
    0.20
    çĮ®
    0.20
    إعÙĦاÙħ
    0.20
     CrossAxisAlignment
    0.19
    Activations Density 0.023%

    No Known Activations