© 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. 65294
    Prev
    Next
    INDEX
    Explanations

    subject matter and subjective experience

    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
    ¾
    -0.08
    ¬
    -0.08
    ÑĪÑĤ
    -0.07
    statt
    -0.07
    beau
    -0.07
    кÑĥда
    -0.07
    ethyst
    -0.07
    baugh
    -0.07
    IENT
    -0.07
    eras
    -0.07
    POSITIVE LOGITS
    ivity
    0.13
    ivism
    0.12
    hood
    0.11
    ivation
    0.09
    ive
    0.09
    ivist
    0.09
    ively
    0.09
    ually
    0.08
    èĥ½åĬ¨æĢ§
    0.08
    urally
    0.08
    Activations Density 0.033%

    No Known Activations