© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23526
    Prev
    Next
    INDEX
    Explanations

    annihilation, anti-matter

    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
    atoon
    -0.08
    uite
    -0.07
    ieste
    -0.07
    ellate
    -0.07
    igts
    -0.07
    aute
    -0.07
     independents
    -0.07
    orum
    -0.07
    leti
    -0.07
     vara
    -0.07
    POSITIVE LOGITS
     annihil
    0.08
    HC
    0.08
    ç²Ĵ
    0.08
    apat
    0.08
    å±ij
    0.07
    æ¯ģçģŃ
    0.07
    ç²ĴåŃIJ
    0.07
    æĴŀåĩ»
    0.07
     pairs
    0.07
    çģŃ
    0.07
    Activations Density 0.005%

    No Known Activations