© 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. 26658
    Prev
    Next
    INDEX
    Explanations

    energy states and structure

    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
    auge
    -0.08
    æī§
    -0.08
    egas
    -0.07
    çĥŃéŨæłĩçŃ¾
    -0.07
    åıĺéĩıçļĦ
    -0.07
    schnitt
    -0.07
     cadr
    -0.07
    åħ¬å®³
    -0.07
    ayar
    -0.07
    ĩ´
    -0.07
    POSITIVE LOGITS
     structure
    0.09
    structure
    0.08
    _structure
    0.07
     ladder
    0.07
    گاÙĩ
    0.07
    ê°
    0.07
    è·ĥ
    0.07
     Structure
    0.07
    ç»ĵæŀĦ
    0.07
    oir
    0.07
    Activations Density 0.011%

    No Known Activations