© 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. 57281
    Prev
    Next
    INDEX
    Explanations

    plastid, chloroplast, cellular, center

    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
    èĤ¡éª¨å¤´
    -0.07
    ack
    -0.07
    çĬ¯
    -0.07
    egos
    -0.07
    èµ°å¼±
    -0.07
    é³Ħ
    -0.07
    elf
    -0.07
    款
    -0.07
    èĥĮåIJİ
    -0.07
    meno
    -0.07
    POSITIVE LOGITS
    åĨħè¿Ľè¡Į
    0.12
    åĨħçļĦ
    0.09
    ãģ§è¡Į
    0.08
     confines
    0.08
    ä¸Ńè¿Ľè¡Į
    0.08
    åĨħ设
    0.08
    åĨħæľī
    0.07
    åħ§çļĦ
    0.07
    æ·±å¤Ħ
    0.07
    partment
    0.07
    Activations Density 0.023%

    No Known Activations