© 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. 34103
    Prev
    Next
    INDEX
    Explanations

    data processing and modification

    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
    çĽĬ
    -0.07
     Apprec
    -0.07
    lob
    -0.07
    å°½æľī
    -0.06
    æĬ±
    -0.06
    为己
    -0.06
     Benefit
    -0.06
    æľīåĬ©
    -0.06
    оÑĢÑĤа
    -0.06
    好å¤Ħ
    -0.06
    POSITIVE LOGITS
    çIJ
    0.07
    æĬĢæľ¯éĹ®é¢ĺ
    0.07
    å¾·åįİ
    0.07
    masalah
    0.07
    _cursor
    0.07
     ÑģоглаÑģно
    0.07
    XL
    0.07
    XY
    0.07
    _logic
    0.06
    .subscriptions
    0.06
    Activations Density 0.001%

    No Known Activations