© 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. 38744
    Prev
    Next
    INDEX
    Explanations

    firearm types

    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
    幡
    -0.09
    å±ĪåİŁ
    -0.08
    æĢªåħ½
    -0.08
    monster
    -0.07
    çĭ®åŃIJ
    -0.07
    orme
    -0.07
    guer
    -0.07
     Grove
    -0.07
    åĬĽå£«
    -0.07
    ionale
    -0.07
    POSITIVE LOGITS
    å°Ħ
    0.15
    å°Ħç¨ĭ
    0.13
    çŀĦåĩĨ
    0.13
    å°Ħåĩ»
    0.11
     firearm
    0.11
     firearms
    0.11
    Shot
    0.10
    å°Ħåĩº
    0.10
     muzzle
    0.10
     pistol
    0.10
    Activations Density 0.150%

    No Known Activations