© 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. 42228
    Prev
    Next
    INDEX
    Explanations

    relationships with other words

    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
    æĨ¬
    -0.07
    åIJīå®ī
    -0.07
    rouw
    -0.07
    Ori
    -0.07
    JM
    -0.07
    åİī害äºĨ
    -0.06
    微信åħ¬ä¼Ĺåı·
    -0.06
    èijĨ
    -0.06
    amble
    -0.06
    sworth
    -0.06
    POSITIVE LOGITS
     pertinent
    0.10
     entirety
    0.08
     aforementioned
    0.07
    çĶļèĩ³æĺ¯
    0.07
     presently
    0.07
     foregoing
    0.07
    iben
    0.07
     amongst
    0.07
    ä½Ĩåį´
    0.06
     respective
    0.06
    Activations Density 2.182%

    No Known Activations