© 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. 62281
    Prev
    Next
    INDEX
    Explanations

    Grand Prix, Grand, .Parameter, .pdf, .org

    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
    ekom
    -0.09
    chia
    -0.08
    scy
    -0.08
    SizeMode
    -0.08
    æľ¬ç«ĻåĨħ容
    -0.08
    ingas
    -0.08
    nitz
    -0.08
    cione
    -0.08
    æ²IJæµ´
    -0.07
    mpz
    -0.07
    POSITIVE LOGITS
    è®°
    0.06
    æī§
    0.06
    è¿ľæµģ
    0.06
    æŃ»
    0.06
    æī¾
    0.06
    @
    0.06
    说
    0.06
    εί
    0.06
    说çļĦ
    0.05
    æīŃåĬĽ
    0.05
    Activations Density 0.308%

    No Known Activations