© 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. 2377
    Prev
    Next
    INDEX
    Explanations

    and followed by a 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
    laud
    -0.08
    ä¹ĭæīĢ以
    -0.08
    лиÑĤ
    -0.07
    çļĦä»ĸ
    -0.07
     tentu
    -0.07
    ellow
    -0.07
     shalt
    -0.06
     Äĩete
    -0.06
    lide
    -0.06
    ยà¹Īà¸Ńม
    -0.06
    POSITIVE LOGITS
     there
    0.10
    rame
    0.10
    rames
    0.09
    ãģĭãģ¤
    0.09
    å·¥ä½ľæĺ¯
    0.09
    æľīè¶³å¤ŁçļĦ
    0.08
     пÑĢиÑģÑĥÑĤÑģÑĤвÑĥеÑĤ
    0.08
    å°±éĤ£ä¹Ī
    0.08
    /how
    0.08
     somehow
    0.08
    Activations Density 0.110%

    No Known Activations