© 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. 8319
    Prev
    Next
    INDEX
    Explanations

    Prähofer-Spohn scaling functions

    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
    å°±åĥıä¸Ģ个
    -0.08
    å¾Īå¤ļä¸ľè¥¿
    -0.07
    ANTED
    -0.07
    éĨ
    -0.07
    olec
    -0.07
    éal
    -0.07
    éĩĮéĿ¢
    -0.07
    nton
    -0.07
    è¿Ļç§įæĥħåĨµ
    -0.07
    olean
    -0.07
    POSITIVE LOGITS
    alsa
    0.07
    agni
    0.07
    èĢģåİ»
    0.07
    aging
    0.06
    jax
    0.06
    \"\
    0.06
    elf
    0.06
    寿
    0.06
    âĢ
    0.06
    ijen
    0.06
    Activations Density 0.005%

    No Known Activations