© 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. 39318
    Prev
    Next
    INDEX
    Explanations

    neutron activation analysis

    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
    æĬĺ
    -0.08
    fold
    -0.07
     fold
    -0.07
     folds
    -0.07
    æĬĺåıł
    -0.07
    velop
    -0.06
     organizing
    -0.06
    èĮĹ
    -0.06
     Fold
    -0.06
    PJ
    -0.06
    POSITIVE LOGITS
    _targets
    0.09
    éĿ¶
    0.09
     targeting
    0.09
     bombard
    0.08
     radioactive
    0.08
    Targets
    0.08
    Via
    0.08
    via
    0.08
     vÃŃa
    0.08
    xen
    0.08
    Activations Density 0.015%

    No Known Activations