© 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. 61052
    Prev
    Next
    INDEX
    Explanations

    collateral dominanc

    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
    æĹłåĬ©
    -0.07
    мо
    -0.07
    æĹłåĬĽ
    -0.07
    æĹłèĢ»
    -0.07
    ober
    -0.07
    ivant
    -0.06
    uat
    -0.06
    åİ®
    -0.06
    ipro
    -0.06
    æĹłæŃ¢
    -0.06
    POSITIVE LOGITS
     dominant
    0.12
     dominance
    0.10
     dominante
    0.09
     Domin
    0.09
     dominate
    0.09
     dominates
    0.09
    erson
    0.08
     majority
    0.08
    _RCC
    0.08
    ecta
    0.08
    Activations Density 0.013%

    No Known Activations