© 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. 46078
    Prev
    Next
    INDEX
    Explanations

    entity relations

    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
     billig
    -0.22
    brtc
    -0.22
    afür
    -0.21
     Erectile
    -0.20
     Ngb
    -0.20
    .FontStyle
    -0.20
     Alv
    -0.20
    缸
    -0.20
    ventory
    -0.20
     */č↵č↵č↵
    -0.20
    POSITIVE LOGITS
    å§ĭ建
    0.25
    æŃ£å®Ĺ
    0.20
    sole
    0.19
     Bro
    0.19
    UTERS
    0.18
    [sizeof
    0.17
    åĬ©çIJĨ
    0.17
    lich
    0.17
     FormGroup
    0.17
    lut
    0.17
    Activations Density 0.001%

    No Known Activations