© 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. 32789
    Prev
    Next
    INDEX
    Explanations

    generating hypotheses

    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
     pledged
    -0.07
    skal
    -0.07
    conse
    -0.07
     thÆ°á»Ľc
    -0.06
    为éļ¾
    -0.06
    Basket
    -0.06
    .inject
    -0.06
    éļĺ
    -0.06
    special
    -0.06
    uÅŁ
    -0.06
    POSITIVE LOGITS
     hypotheses
    0.13
     hypothesis
    0.10
    大èĥĨ
    0.09
    æݨæµĭ
    0.09
     conject
    0.09
    çĮľæĥ³
    0.09
     tentative
    0.08
     vermut
    0.08
     guesses
    0.08
    ãĤĴç«ĭãģ¦
    0.08
    Activations Density 0.008%

    No Known Activations