© 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. 41692
    Prev
    Next
    INDEX
    Explanations

    alleles and genotypes

    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
    ignum
    -0.07
    缸è¾ħ缸æĪIJ
    -0.07
    åıijæī¬
    -0.07
     smoother
    -0.07
    ream
    -0.07
    incid
    -0.07
     smoothed
    -0.07
    entine
    -0.06
    ÑĪне
    -0.06
    飲
    -0.06
    POSITIVE LOGITS
    AZE
    0.07
    confirmed
    0.07
    ARA
    0.07
    OrFail
    0.07
    оби
    0.07
    ï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭ
    0.07
    Confirmed
    0.07
     Assurance
    0.07
    çĪĽ
    0.06
    ogan
    0.06
    Activations Density 0.002%

    No Known Activations