© 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. 50191
    Prev
    Next
    INDEX
    Explanations

    ’ve been

    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
    âĢ¦
    -0.07
    Âł
    -0.07
    åħ¸
    -0.06
    ox
    -0.06
    ewa
    -0.06
    «
    -0.06
    âĤ¬
    -0.06
    ble
    -0.06
    _kwargs
    -0.06
     ev
    -0.06
    POSITIVE LOGITS
    ersen
    0.09
    erne
    0.09
    inte
    0.08
    θο
    0.08
    æľįåĬ¡å¥½
    0.08
    æī¦
    0.08
    atorio
    0.08
    erring
    0.08
    ropy
    0.08
    箸
    0.07
    Activations Density 0.039%

    No Known Activations