© 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. 57463
    Prev
    Next
    INDEX
    Explanations

    factorization, fixed effect, heterogeneity, lambda\_j

    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
    /native
    -0.09
    astics
    -0.07
    _VARS
    -0.07
    伪åĬ£
    -0.07
    orest
    -0.07
    arate
    -0.07
     Symbol
    -0.07
     native
    -0.07
    ikle
    -0.07
     Tutt
    -0.07
    POSITIVE LOGITS
    éļ
    0.09
    缸çľĭ
    0.08
    强åĬ¿
    0.07
    ç²ĭ
    0.07
    æ´»
    0.07
    çIJħ
    0.07
    endency
    0.07
    笳
    0.06
    åĽļ
    0.06
    _reload
    0.06
    Activations Density 0.007%

    No Known Activations