© 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. 23049
    Prev
    Next
    INDEX
    Explanations

    cross-rays, house, cheese

    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|>
    -0.10
    celli
    -0.07
    èį¼
    -0.07
    .addListener
    -0.07
    cule
    -0.07
     másc
    -0.07
    erst
    -0.07
    髦
    -0.07
    MeshPro
    -0.07
    ç¼ĸè¾ijäºİ
    -0.07
    POSITIVE LOGITS
    åĴĮçĶ°
    0.07
    èĩ´
    0.06
     Düsseldorf
    0.06
     dén
    0.06
    ÑģÑĤÑĢÑĭ
    0.06
    kup
    0.06
    ä¹Łä¸Ģ缴
    0.06
    éĤ£åº§
    0.06
    itals
    0.06
    itul
    0.06
    Activations Density 0.296%

    No Known Activations