© 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. 39017
    Prev
    Next
    INDEX
    Explanations

    guidelines and protocols

    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
     —
    -0.06
    oin
    -0.06
     (
    -0.06
    metic
    -0.06
    ä¹Ī
    -0.06
    åį´
    -0.06
     blah
    -0.06
    对åIJ§
    -0.05
    对è¿Ļ个
    -0.05
    çĹ´
    -0.05
    POSITIVE LOGITS
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.14
     infine
    0.12
    çļĦåħ¶ä»ĸ
    0.10
     enfin
    0.10
     insomma
    0.10
    çŃīåħ¶ä»ĸ
    0.10
    ONUS
    0.09
    æľ¬èº«çļĦ
    0.09
    æss
    0.09
    åĢ¼å¾Ĺä¸ĢæıIJçļĦæĺ¯
    0.09
    Activations Density 0.010%

    No Known Activations