© 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. 19275
    Prev
    Next
    INDEX
    Explanations

    Dr. lives, resonance imaging, mail server, career strategy

    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
    "":
    -0.08
    utom
    -0.08
    å¤ļèĬ¬
    -0.08
    apta
    -0.08
    åħ¶æŀĹ
    -0.08
    uzzi
    -0.08
    æŶæĹ¥
    -0.08
    ingga
    -0.08
    åĪĩå®ŀåģļ好
    -0.08
    AspNet
    -0.08
    POSITIVE LOGITS
    å°ij
    0.06
     nonlinear
    0.06
    éĿŀ线æĢ§
    0.06
     Certain
    0.06
     certain
    0.06
    _ENCODE
    0.06
    yt
    0.06
    gear
    0.06
    没
    0.06
     Cooper
    0.05
    Activations Density 0.520%

    No Known Activations