© 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. 24347
    Prev
    Next
    INDEX
    Explanations

    eigen states and values

    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
    orme
    -0.08
    _ratio
    -0.08
    (trace
    -0.07
    è·Łè¸ª
    -0.07
     kümm
    -0.07
     dov
    -0.07
    insk
    -0.07
    ousing
    -0.07
    /tiny
    -0.07
    unya
    -0.07
    POSITIVE LOGITS
    çŃĶ
    0.07
    ÑĢио
    0.07
     states
    0.07
    å®Įå¤ĩ
    0.07
    æľīåij³
    0.07
    ÑĹв
    0.07
    nowledge
    0.07
    ALER
    0.07
     declar
    0.06
    urable
    0.06
    Activations Density 0.004%

    No Known Activations