© 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. 32845
    Prev
    Next
    INDEX
    Explanations

    original message

    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
    ãĥ³
    -0.08
    ìį¨
    -0.08
    à¹Ĩ
    -0.07
    ungs
    -0.07
    anh
    -0.07
    á»ijc
    -0.07
    ed
    -0.07
    prat
    -0.07
    istic
    -0.06
    minster
    -0.06
    POSITIVE LOGITS
    eam
    0.09
    Ø©
    0.08
    eil
    0.08
    翼翼
    0.07
    Õµ
    0.07
    íĥĢìļ´
    0.07
    اض
    0.07
    ablish
    0.07
    Ñĩек
    0.06
    quential
    0.06
    Activations Density 0.010%

    No Known Activations