© 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. 34058
    Prev
    Next
    INDEX
    Explanations

    manganese or Mn

    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
    rette
    -0.09
    -fashioned
    -0.08
    ly
    -0.07
    matic
    -0.07
    een
    -0.07
    ally
    -0.07
    enza
    -0.07
    etés
    -0.07
    rett
    -0.07
    ़
    -0.07
    POSITIVE LOGITS
    çĻ¾èįī
    0.09
    éħ¸éĴ¾
    0.09
    yota
    0.08
    lessly
    0.07
    обÑĭ
    0.07
    ergestellt
    0.07
    voud
    0.07
    غاÙħ
    0.07
    lehr
    0.07
    fade
    0.07
    Activations Density 0.048%

    No Known Activations