© 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. 62342
    Prev
    Next
    INDEX
    Explanations

    along with others

    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
    æĹ¢æľī
    -0.08
    åIJİèĢħ
    -0.07
    IFI
    -0.07
    ernen
    -0.07
    å®ŀå¤Ħ
    -0.07
    blr
    -0.07
    å¹²éĥ¨çļĦ
    -0.07
    两èĢħ
    -0.07
    罡
    -0.07
    强强
    -0.07
    POSITIVE LOGITS
     other
    0.13
     others
    0.11
    other
    0.11
    åħ¶ä»ĸçļĦ
    0.10
    åħ¶å®ĥçļĦ
    0.10
    åħ¶ä»ĸ
    0.10
    åħ¶å®ĥ
    0.10
     otros
    0.10
    -other
    0.10
    åħ¶ä½Ļ
    0.09
    Activations Density 0.372%

    No Known Activations