© 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. 42980
    Prev
    Next
    INDEX
    Explanations

    succinct descriptions

    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
    owan
    -0.08
    μÏĨ
    -0.07
    oz
    -0.07
    ajor
    -0.07
    åŃ¦è¯´
    -0.07
    ntag
    -0.07
    讹
    -0.07
    é¢ij次
    -0.07
    éºŁ
    -0.06
    åı·éĻ¢
    -0.06
    POSITIVE LOGITS
    ness
    0.09
    à¤Ī
    0.09
    ly
    0.08
     enough
    0.08
    ances
    0.08
    NESS
    0.08
    ä¸ĢäºĽçļĦ
    0.07
    unica
    0.07
    ely
    0.07
    zza
    0.07
    Activations Density 0.001%

    No Known Activations