© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17187
    Prev
    Next
    INDEX
    Explanations

    lattice distortion or deformation

    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
    ids
    -0.07
    å¹³çŃī
    -0.07
     Bestand
    -0.06
     cap
    -0.06
    æĮ¡
    -0.06
    åĪĴ
    -0.06
    åħ¬å¹³
    -0.06
    æ¦Ĥ
    -0.06
     responsibly
    -0.06
    etsk
    -0.06
    POSITIVE LOGITS
     distortion
    0.11
    åģı离
    0.10
     distort
    0.10
     deform
    0.09
    çķ¸
    0.09
    æīŃæĽ²
    0.09
    以éĢĤåºĶ
    0.09
     deformation
    0.08
    èĪĴå±ķ
    0.08
    è®Ĭå½¢
    0.08
    Activations Density 0.012%

    No Known Activations