© 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. 29122
    Prev
    Next
    INDEX
    Explanations

    except in compliance

    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
    irti
    -0.09
    incontro
    -0.09
    warts
    -0.09
    èī²åĪĹ
    -0.08
    ÑĢож
    -0.08
    ä»»ä½ł
    -0.08
    enção
    -0.08
    ä¸Ģ路走æĿ¥
    -0.08
    .obtain
    -0.08
    vidia
    -0.08
    POSITIVE LOGITS
    (
    0.06
     ↵
    0.06
    el
    0.06
    çIJ¦
    0.06
    VS
    0.05
    èĬĻ
    0.05
    1
    0.05
    vs
    0.05
    Âł
    0.05
    éĿłèĩªå·±
    0.05
    Activations Density 0.856%

    No Known Activations