© 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. 44086
    Prev
    Next
    INDEX
    Explanations

    of plus a general word

    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
    ä¸įèĥ½å¤Ł
    -0.08
    olong
    -0.08
    ittings
    -0.08
    /hooks
    -0.08
     opdr
    -0.08
    ipy
    -0.07
    orage
    -0.07
    wner
    -0.07
    одо
    -0.07
    oga
    -0.07
    POSITIVE LOGITS
    æŃ¤èµ·
    0.07
    rick
    0.07
    åħ¶ä¸Ńæľī
    0.07
    alic
    0.06
    åħ¶ä¸ŃåĮħæĭ¬
    0.06
    ached
    0.06
    çĶ±æѤ
    0.06
    åħ¶ä¸Ń
    0.06
    chie
    0.06
    £¼
    0.06
    Activations Density 0.709%

    No Known Activations