© 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-CHAT-65K
    7. 46489
    Prev
    Next
    INDEX
    Explanations

    feel listened to

    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/lmsys/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 192 tokens each
    Dataset (Dashboard)
    chanind/lmsys-chat-1m-qwen-2.5
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Interracial
    -0.26
    计åħ¥
    -0.22
    przed
    -0.21
    ucer
    -0.20
     Gim
    -0.20
    	ERROR
    -0.19
     frankfurt
    -0.19
    PCS
    -0.19
    VV
    -0.19
    pert
    -0.19
    POSITIVE LOGITS
    (strpos
    0.22
     rex
    0.19
    çľ©
    0.18
    Backdrop
    0.18
    ãĤ¨ãĤ¹ãĥĨ
    0.18
    chen
    0.18
    []=$
    0.18
    opcion
    0.18
     strugg
    0.18
    ãĤ¢ãĤ¸
    0.18
    Activations Density 0.001%

    No Known Activations