© 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. 17060
    Prev
    Next
    INDEX
    Explanations

    copyright notice, this list of conditions

    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
    oley
    -0.09
    opter
    -0.08
    éĤ£éĩĮ
    -0.08
    ekh
    -0.08
    orners
    -0.08
    croll
    -0.08
    abaj
    -0.08
    zata
    -0.08
    /Gate
    -0.07
    åĨįä¸į
    -0.07
    POSITIVE LOGITS
    _pad
    0.07
    ucch
    0.07
    ndl
    0.07
    çĮ«
    0.07
    ragt
    0.07
    å§ĵ
    0.06
     Tar
    0.06
    iae
    0.06
    ÏĦαν
    0.06
    nga
    0.06
    Activations Density 0.007%

    No Known Activations