© 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. 42874
    Prev
    Next
    INDEX
    Explanations

    other variations

    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
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.08
    ziem
    -0.06
    fahr
    -0.06
    濯
    -0.06
    ami
    -0.06
    è¶ħä¹İ
    -0.06
    eel
    -0.06
    ibra
    -0.05
    èİ«
    -0.05
     Alam
    -0.05
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.16
     other
    0.15
    åħ¶å®ĥçļĦ
    0.14
    åħ¶ä»ĸ
    0.14
    çļĦåħ¶ä»ĸ
    0.14
    åħ¶ä»ĸçļĦ
    0.14
     otras
    0.14
     outras
    0.13
    åħ¶å®ĥ
    0.13
    other
    0.13
    Activations Density 0.500%

    No Known Activations