© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55025
    Prev
    Next
    INDEX
    Explanations

    mapping fiber products

    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
    Negative Logits
     Pern
    -0.08
    éĢĬ
    -0.06
    åĢ©
    -0.06
    /frame
    -0.06
    á»±a
    -0.06
    ä¸įèĥ½åĨį
    -0.06
    çĶ«
    -0.06
    dB
    -0.06
     Dim
    -0.06
    eko
    -0.06
    POSITIVE LOGITS
    éĤ¸
    0.08
    obr
    0.08
    åĿ
    0.08
     Mapping
    0.08
    驻马
    0.08
    éĤ£ä¹ĪçļĦ
    0.08
    mapping
    0.08
    obiet
    0.08
    eros
    0.07
     mapping
    0.07
    Activations Density 0.005%

    No Known Activations