© 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. 38357
    Prev
    Next
    INDEX
    Explanations

    nuclei, nuclear, neutron

    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
    èĩªå·±çļĦè¡Į为
    -0.08
    ulli
    -0.07
     RSVP
    -0.07
    é«ĺéĩĩ
    -0.07
    ört
    -0.07
     timed
    -0.07
    åħľ
    -0.07
    essar
    -0.07
    สà¸ĸ
    -0.07
    _default
    -0.07
    POSITIVE LOGITS
     nucleus
    0.10
     nuclei
    0.09
    æł¸
    0.09
     nuclear
    0.08
     neutron
    0.08
     fragmentation
    0.07
     nuc
    0.07
    -size
    0.07
    idos
    0.07
    åĪĨè£Ĥ
    0.07
    Activations Density 0.003%

    No Known Activations