© 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. 42900
    Prev
    Next
    INDEX
    Explanations

    voltage and volts

    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
     ÏĦÏģο
    -0.08
    jada
    -0.07
    ê°±
    -0.07
     деÑıÑĤелÑĮноÑģÑĤÑĮ
    -0.07
    åıijè¾¾
    -0.07
    æī§
    -0.07
    輩
    -0.07
     dias
    -0.07
    Ñģле
    -0.07
    ãĥĥãĤ·
    -0.07
    POSITIVE LOGITS
    çĶµåİĭ
    0.11
     voltage
    0.11
    oltage
    0.10
     volts
    0.10
    Voltage
    0.09
     Voltage
    0.09
    è¾ĵåĩºçĶµåİĭ
    0.08
     volt
    0.08
    _voltage
    0.08
    端åŃIJ
    0.08
    Activations Density 0.023%

    No Known Activations