© 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. 56750
    Prev
    Next
    INDEX
    Explanations

    outcomes and results

    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
    tain
    -0.08
    plements
    -0.07
    åħ¬åħ±é¢Ħç®Ĺ
    -0.07
    ve
    -0.07
    ordinator
    -0.06
    Öģ
    -0.06
    é£İ头
    -0.06
    æīį
    -0.06
    åĬŁåĬ³
    -0.06
    ovit
    -0.06
    POSITIVE LOGITS
     consequences
    0.17
    çļĦåIJİæŀľ
    0.16
    åIJİæŀľ
    0.16
     implications
    0.15
     consequence
    0.15
     conséquences
    0.14
     ramifications
    0.14
     repercussions
    0.13
     consecuencias
    0.13
     conseguenze
    0.13
    Activations Density 0.110%

    No Known Activations