© 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. 50294
    Prev
    Next
    INDEX
    Explanations

    might precede potential outcomes

    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
    <|box_end|>
    -0.12
    strup
    -0.11
    ležité
    -0.10
    ìį¨
    -0.10
    ientos
    -0.10
    hower
    -0.10
    actable
    -0.10
    ption
    -0.09
    ayscale
    -0.09
    ión
    -0.09
    POSITIVE LOGITS
    a
    0.12
     be
    0.11
     saja
    0.09
    t
    0.09
    enticate
    0.08
    ering
    0.08
    ing
    0.08
    y
    0.08
    ëĤĺ
    0.07
    s
    0.07
    Activations Density 0.102%

    No Known Activations