© 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. 47073
    Prev
    Next
    INDEX
    Explanations

    greater than or equal to

    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
    éra
    -0.09
    atur
    -0.09
    meister
    -0.08
    бил
    -0.08
    ÙĪارÙĩ
    -0.08
    ÅĤon
    -0.07
    apel
    -0.07
    hey
    -0.07
    orama
    -0.07
    ATUR
    -0.07
    POSITIVE LOGITS
    以åıĬ
    0.07
    (IP
    0.06
    ousand
    0.06
    Õ®
    0.06
     ("
    0.06
    tha
    0.06
    ackers
    0.06
    Ł
    0.06
    (si
    0.06
     (*
    0.06
    Activations Density 0.015%

    No Known Activations