© 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. 47006
    Prev
    Next
    INDEX
    Explanations

    inspirational and positive experiences

    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
    å½¢åĬ¿
    -0.08
    åĪ©å®³
    -0.08
    åıĤæĶ¿
    -0.07
    ä¸įèĥľæĶ¶
    -0.06
    yek
    -0.06
     facto
    -0.06
    ritis
    -0.06
    åħ¬çĦ¶
    -0.06
    ī
    -0.06
    reme
    -0.06
    POSITIVE LOGITS
     âĿ¤
    0.09
    RIES
    0.08
    ittel
    0.08
    بس
    0.08
     imprend
    0.08
     âĻ¥
    0.08
     вдоÑħ
    0.08
    voll
    0.08
    alej
    0.07
     spoko
    0.07
    Activations Density 1.265%

    No Known Activations