© 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. 45546
    Prev
    Next
    INDEX
    Explanations

    bibliographic references

    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
    èī¾çijŀ
    -0.07
    scratch
    -0.07
     Pek
    -0.07
    é¦ĸå¯Į
    -0.07
    åħįè´¹éĺħ读
    -0.06
    夷
    -0.06
    çļĦåĽŀ
    -0.06
    EMENT
    -0.06
    ãģ£ãģ±ãĤĬ
    -0.06
    ç»ıæµİæĮĩæłĩ
    -0.06
    POSITIVE LOGITS
    ¸
    0.08
    ustes
    0.07
    iose
    0.06
     UIL
    0.06
    erecht
    0.06
    autop
    0.06
    uges
    0.06
    èĦĸ
    0.06
    ard
    0.06
    yen
    0.06
    Activations Density 0.001%

    No Known Activations