© 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. 47324
    Prev
    Next
    INDEX
    Explanations

    volume and measurement units

    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
    宽带
    -0.08
    çļĦåĬĽåº¦
    -0.08
     band
    -0.08
     bands
    -0.07
    estre
    -0.07
    Band
    -0.07
    éŁ
    -0.07
    ç©Ĩ
    -0.07
    强度
    -0.07
    çĶµå¹³
    -0.06
    POSITIVE LOGITS
    容积
    0.19
     volume
    0.19
     volumes
    0.18
    ä½ĵ积
    0.18
    -volume
    0.17
    volume
    0.17
    .volume
    0.17
     Volume
    0.16
    olumes
    0.16
     volumen
    0.16
    Activations Density 0.023%

    No Known Activations