© 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. 3277
    Prev
    Next
    INDEX
    Explanations

    your

    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
     proper
    -0.24
     Proper
    -0.21
     properly
    -0.21
    èĩªå¾ĭ
    -0.21
    proper
    -0.20
    rysler
    -0.20
    ç»ĻæĪij们
    -0.20
    eref
    -0.20
    æĪij们å¿ħé¡»
    -0.19
     ADVISED
    -0.19
    POSITIVE LOGITS
     yourself
    0.24
     your
    0.24
     createState
    0.24
    ä½łçļĦ
    0.24
    your
    0.24
    ModelError
    0.22
    angered
    0.21
     }):
    0.20
    odate
    0.20
    Your
    0.20
    Activations Density 0.268%

    No Known Activations