© 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. 13553
    Prev
    Next
    INDEX
    Explanations

    similarly, likewise, same

    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
    éĤ£åı¯æĺ¯
    -0.07
    indle
    -0.07
     nonetheless
    -0.07
    åħĪä»İ
    -0.07
    é½IJå¿ĥåįıåĬĽ
    -0.06
    usch
    -0.06
     nevertheless
    -0.06
    usser
    -0.06
     tatsächlich
    -0.06
    åį´æĺ¯
    -0.06
    POSITIVE LOGITS
    åIJĮçIJĨ
    0.13
     similarly
    0.13
     ë§Īì°¬ê°Ģì§Ģë¡ľ
    0.13
    亦çĦ¶
    0.13
    Similarly
    0.12
     Similarly
    0.12
     ë§Īì°¬ê°Ģì§Ģ
    0.11
    similar
    0.10
    类似çļĦ
    0.10
     likewise
    0.10
    Activations Density 0.086%

    No Known Activations