© 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. 43081
    Prev
    Next
    INDEX
    Explanations

    LICENSE file

    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
    вакÑĥ
    -0.08
    øl
    -0.08
    .struct
    -0.08
    nikov
    -0.08
    biet
    -0.07
    ק×Ķ
    -0.07
    ARTH
    -0.07
    æ½ľåħ¥
    -0.07
    ä¹ŁçĶ±
    -0.07
    ULER
    -0.07
    POSITIVE LOGITS
    æĨ§
    0.07
    .vs
    0.07
    åįĵ
    0.06
    uffer
    0.06
    çĸ¾
    0.06
    az
    0.06
    æºĸ
    0.06
    atform
    0.06
     Tore
    0.06
     intu
    0.06
    Activations Density 0.001%

    No Known Activations