© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30184
    Prev
    Next
    INDEX
    Explanations

    good followed by quality or food

    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
    tlement
    -0.09
    entions
    -0.08
    eves
    -0.08
    ént
    -0.08
    Ò£
    -0.08
    годно
    -0.08
    езд
    -0.08
    entrum
    -0.08
    ãģ£ãģįãĤĬ
    -0.08
    inking
    -0.08
    POSITIVE LOGITS
    liness
    0.11
    smith
    0.10
    yssey
    0.10
    zilla
    0.10
    ness
    0.10
    zinho
    0.10
    liest
    0.09
    er
    0.09
    reau
    0.08
    lessly
    0.08
    Activations Density 0.090%

    No Known Activations