© 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. 18055
    Prev
    Next
    INDEX
    Explanations

    population dynamics and census

    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
     genu
    -0.08
    lessly
    -0.08
    -shared
    -0.07
     Bez
    -0.07
    itan
    -0.07
     поÑģÑĤоÑĢон
    -0.07
    éĢļè¿ĩæŃ¤æ¬¡
    -0.07
     gratt
    -0.07
     incidente
    -0.07
     мол
    -0.07
    POSITIVE LOGITS
    ç¹ģæ®ĸ
    0.12
    ç§į群
    0.10
    åŁºæķ°
    0.10
     populations
    0.10
     census
    0.10
    ç¹ģè¡į
    0.09
     population
    0.09
     reproductive
    0.09
     births
    0.09
     stocks
    0.09
    Activations Density 0.007%

    No Known Activations