© 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. 33935
    Prev
    Next
    INDEX
    Explanations

    "No you can't"

    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
     praised
    -0.08
    åħģ
    -0.08
    anaf
    -0.08
    é¼ĵèĪŀ
    -0.08
    éħ¬
    -0.08
    .outputs
    -0.07
     rejuven
    -0.07
    çĦķ
    -0.07
    åªļ
    -0.07
    ENABLE
    -0.07
    POSITIVE LOGITS
    éĺ»æŃ¢
    0.11
    æĭĴç»Ŀ
    0.10
     rejection
    0.10
    åĬĿéĺ»
    0.10
    Reject
    0.10
     rejecting
    0.10
     preventing
    0.09
    reject
    0.09
     discour
    0.09
     запÑĢ
    0.09
    Activations Density 0.173%

    No Known Activations