© 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. 19326
    Prev
    Next
    INDEX
    Explanations

    observation or noticing

    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
     envisioned
    -0.08
    ope
    -0.07
    iser
    -0.07
    szak
    -0.07
    ity
    -0.07
    å°Ĩèĩ³
    -0.07
    ä¸ĢåŃĹ
    -0.07
    è·ĭæ¶ī
    -0.07
    ansion
    -0.07
    forth
    -0.07
    POSITIVE LOGITS
    è§Ĥå¯Ł
    0.13
     observations
    0.13
    observations
    0.12
    è§Ĥå¯ŁåĪ°
    0.12
     observation
    0.12
    observation
    0.11
    è§Ģå¯Ł
    0.10
     ê´Ģì°°
    0.10
     Observation
    0.10
    observe
    0.10
    Activations Density 0.057%

    No Known Activations