© 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. 26399
    Prev
    Next
    INDEX
    Explanations

    randomly assign or redistribute

    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
    iglio
    -0.08
    大åIJį
    -0.08
    atk
    -0.08
    bsub
    -0.08
    viz
    -0.08
    ä¸İæĸ¹æ³ķ
    -0.07
    vens
    -0.07
    è¦ģæ±Ĥèĩªå·±
    -0.07
    ontro
    -0.07
    åĽ½éĻħåĮĸ
    -0.07
    POSITIVE LOGITS
    ança
    0.06
    Sup
    0.06
    对è§Ĩ
    0.06
    нибÑĥдÑĮ
    0.05
    sup
    0.05
    (
    0.05
     
    0.05
    æĹ¨åľ¨
    0.05
    ajar
    0.05
    å§ĭ
    0.05
    Activations Density 0.009%

    No Known Activations