© 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. 47342
    Prev
    Next
    INDEX
    Explanations

    conceptually.getOwnPropertyposted date/time

    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
    çīµ
    -0.07
    åij½ä¸Ń
    -0.07
    å±±éķĩ
    -0.06
    以ä¸ĭ为
    -0.06
    åħ¶æ¬¡
    -0.06
    æłĩ示
    -0.06
    éļıæĦı
    -0.06
    æĢģ
    -0.06
    æĥ³èµ·
    -0.06
    zk
    -0.06
    POSITIVE LOGITS
    éĻħ
    0.08
    .getOwnProperty
    0.08
    eting
    0.08
    itness
    0.07
    appings
    0.07
    arden
    0.07
    emes
    0.07
    etry
    0.07
    atica
    0.07
    æĺ¥å¤ıç§ĭåĨ¬
    0.07
    Activations Density 0.005%

    No Known Activations