© 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. 33204
    Prev
    Next
    INDEX
    Explanations

    audience responses

    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
    맹
    -0.07
    atty
    -0.07
    åħ¸
    -0.07
    å¾Ħ
    -0.07
    nom
    -0.07
    idd
    -0.07
    nhard
    -0.07
    ining
    -0.07
    imit
    -0.07
    emento
    -0.07
    POSITIVE LOGITS
    ience
    0.08
    姥çĪ·
    0.07
    asai
    0.07
    ees
    0.07
    å¸Ń
    0.07
    æł¼åħ°
    0.07
    -facing
    0.07
    Ø©
    0.07
    èĢģçĪ·
    0.07
    esia
    0.07
    Activations Density 0.018%

    No Known Activations