© 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. 29538
    Prev
    Next
    INDEX
    Explanations

    bug numbers and identifiers

    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
    åħ¶å®ĥåªĴä½ĵ
    -0.08
    okit
    -0.07
    -layout
    -0.07
    Inserted
    -0.07
     arou
    -0.07
    èĬ¸
    -0.07
    accumulator
    -0.07
    igram
    -0.07
    oki
    -0.07
    æĸ°éĹ»èĪĨæĥħ
    -0.07
    POSITIVE LOGITS
    akas
    0.08
    馴
    0.07
    éĵ¶å±±
    0.07
    ç¡¬æł¸
    0.06
     caused
    0.06
    gå
    0.06
    主è¦ģæĺ¯çĶ±äºİ
    0.06
    ucker
    0.06
    çıĬ
    0.06
    å¦Ĥæŀľä½łæĺ¯
    0.06
    Activations Density 0.014%

    No Known Activations