© 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. 17170
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    éĻIJæľŁ
    -0.07
    ä¸ľæµ·
    -0.06
    wich
    -0.06
     Proceed
    -0.06
    oh
    -0.06
    loom
    -0.06
    thane
    -0.06
    hammer
    -0.06
    亥
    -0.06
    彬
    -0.06
    POSITIVE LOGITS
     ervan
    0.09
    avo
    0.09
    iating
    0.08
    ä¸ĥçĻ¾
    0.08
     slå
    0.08
    деÑģÑı
    0.08
    esehen
    0.08
    λάÏĩιÏĥ
    0.08
    Interop
    0.08
    _POST
    0.07
    Activations Density 0.000%

    No Known Activations