© 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. 57620
    Prev
    Next
    INDEX
    Explanations

    voltage and signal levels

    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
    ipas
    -0.08
    igl
    -0.08
     observational
    -0.08
    æłij人
    -0.08
    LBL
    -0.07
    ekt
    -0.07
    imus
    -0.07
    ç¼´è´¹
    -0.07
    .inflate
    -0.07
    _SYM
    -0.07
    POSITIVE LOGITS
     signal
    0.10
    signal
    0.09
    çĶµå¹³
    0.09
    ä¿¡åı·
    0.09
     waveform
    0.09
     voltage
    0.09
     Voltage
    0.09
    _signal
    0.08
     signals
    0.08
     Signal
    0.08
    Activations Density 0.061%

    No Known Activations