© 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. 3096
    Prev
    Next
    INDEX
    Explanations

    how to achieve

    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
    inni
    -0.08
    iel
    -0.08
     szenved
    -0.08
    udit
    -0.07
    ±
    -0.07
    äºİä¸Ģ
    -0.07
    uhe
    -0.07
    ovich
    -0.07
     ì§ĵ
    -0.07
    ilde
    -0.07
    POSITIVE LOGITS
    å±ī
    0.07
    æĪ·æĪ·
    0.07
    stem
    0.07
    ä¸įè¾ľè´Ł
    0.07
     construct
    0.06
    ely
    0.06
    æ´²
    0.06
    irement
    0.06
    èİħ
    0.06
    olt
    0.06
    Activations Density 0.052%

    No Known Activations