© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11395
    Prev
    Next
    INDEX
    Explanations

    relativity and Einstein

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    teria
    -0.09
    anee
    -0.09
    åıijå¸ĥåħ¬åijĬ称
    -0.08
    ambre
    -0.08
    æłı
    -0.08
    檻
    -0.08
     presto
    -0.08
    å¹´å§ĭ
    -0.08
    igd
    -0.08
    ditor
    -0.08
    POSITIVE LOGITS
    ith
    0.07
    -inspired
    0.07
    ist
    0.07
    aty
    0.07
    uss
    0.07
    ativity
    0.07
    ists
    0.06
    enberg
    0.06
    ucker
    0.06
    ian
    0.06
    Activations Density 0.003%

    No Known Activations