© 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. 50623
    Prev
    Next
    INDEX
    Explanations

    firefighters, rescue, extinguishing

    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
     chip
    -0.07
    鸡èĤī
    -0.07
    çĥ½çģ«
    -0.07
    带åĬ¨ä¸ĭ
    -0.07
    Chip
    -0.07
    vely
    -0.07
     chips
    -0.07
    åŀĤéĴĵ
    -0.06
     gÃł
    -0.06
    ç£ķ
    -0.06
    POSITIVE LOGITS
     extingu
    0.13
    çģŃçģ«
    0.12
    æķij人
    0.10
    æīijæķij
    0.10
    æ»ħ
    0.10
    æīijçģŃ
    0.10
     firefighters
    0.10
    æ¶Īéĺ²
    0.09
    æĬ¢éĻ©
    0.09
     firefight
    0.09
    Activations Density 0.039%

    No Known Activations