© 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. 15649
    Prev
    Next
    INDEX
    Explanations

    cytok followed by ines

    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
    teness
    -0.07
    agnar
    -0.07
     alun
    -0.07
     amort
    -0.06
    acas
    -0.06
    llx
    -0.06
    issage
    -0.06
     Vest
    -0.06
    åı¯è´µ
    -0.06
    æľīç¼ĺ
    -0.06
    POSITIVE LOGITS
    avanaugh
    0.09
     cytok
    0.09
    indir
    0.08
    奶çĪ¸
    0.08
    itech
    0.08
    -mediated
    0.08
    çĿ
    0.08
    faker
    0.08
    dex
    0.07
     responses
    0.07
    Activations Density 0.098%

    No Known Activations