© 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. 62953
    Prev
    Next
    INDEX
    Explanations

    both, latter, Ambos, ambas

    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
    åĢį
    -0.06
    饶
    -0.06
    ghost
    -0.06
    @c
    -0.06
    å¸ĮæľĽå¯¹å¤§å®¶æľīæīĢ帮åĬ©
    -0.06
    ×£
    -0.06
    .times
    -0.06
    Ñĩие
    -0.06
    èĮĥåĽ´
    -0.06
     ok
    -0.05
    POSITIVE LOGITS
    åIJİèĢħ
    0.11
    ãģĸãģ¾
    0.10
    ãģ©ãģ¡ãĤī
    0.10
     ambos
    0.09
    åīįèĢħ
    0.09
     BOTH
    0.09
     begge
    0.09
    两èĢħ
    0.09
     Ambos
    0.09
     latter
    0.09
    Activations Density 0.114%

    No Known Activations