© 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. 44921
    Prev
    Next
    INDEX
    Explanations

    URLs with sha256 hashes

    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
    ngr
    -0.11
    mdl
    -0.11
    ungk
    -0.10
    cores
    -0.10
    ?>>
    -0.10
    ”âĢ¦
    -0.09
    borough
    -0.09
    .mi
    -0.09
    éĤ£ä¹Ī好
    -0.09
     Numéro
    -0.09
    POSITIVE LOGITS
    -
    0.12
     -
    0.10
    -t
    0.07
    —
    0.07
    -c
    0.07
    -p
    0.07
    -b
    0.07
    de
    0.07
    âĶĢ
    0.06
    ↵
    0.06
    Activations Density 0.002%

    No Known Activations