© 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. 27754
    Prev
    Next
    INDEX
    Explanations

    invention, disclosure, subject, embodiments

    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
    _apply
    -0.08
    åħ¨éĥ¨è¯Ħ论
    -0.08
    æĪijè¦ģè¯Ħ论
    -0.07
    Ñĥда
    -0.07
    çĺ«
    -0.07
    оÑī
    -0.06
    ä½ıæ°ij
    -0.06
    çĽ¸å¯¹èĢĮè¨Ģ
    -0.06
    ê¾¼
    -0.06
     dip
    -0.06
    POSITIVE LOGITS
    å¹ħ
    0.07
    halte
    0.07
    iblio
    0.07
    inous
    0.07
    _SK
    0.07
    åįļçĪ±
    0.06
    ittance
    0.06
    iket
    0.06
    (.)
    0.06
    URS
    0.06
    Activations Density 0.007%

    No Known Activations