© 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. 44935
    Prev
    Next
    INDEX
    Explanations

    pest solution

    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
    inst
    -0.08
    åħĭç½Ĺ
    -0.07
    Fr
    -0.07
    踵
    -0.07
     Coin
    -0.07
    Ko
    -0.06
    她å°Ĩ
    -0.06
    addir
    -0.06
    .sheet
    -0.06
    Rank
    -0.06
    POSITIVE LOGITS
    icz
    0.07
    åĴķ
    0.07
    rego
    0.07
    illy
    0.07
    ä¸ĭä¸Ģç¯ĩ
    0.07
    ä¸Ģ个好çļĦ
    0.06
    forums
    0.06
    éĻ¨
    0.06
     gara
    0.06
    oxy
    0.06
    Activations Density 0.019%

    No Known Activations