© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 32708
    Prev
    Next
    INDEX
    Explanations

    story, edition, or blu-ray text completions

    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
    ."]
    -0.10
    ï¼Ī
    -0.09
    ."),
    -0.09
     ];
    -0.09
    ãĢįï¼Ī
    -0.09
    ï¼ģï¼Ī
    -0.09
    >").
    -0.09
     ]).
    -0.08
    ])),
    -0.08
    ãĢıï¼Ī
    -0.08
    POSITIVE LOGITS
     &)
    0.10
     _)
    0.08
    ç¿°
    0.07
    &)
    0.07
    æĻ®ç½Ĺ
    0.07
    éϤå¤ĸ
    0.07
    åĪĨ许
    0.07
     {})
    0.07
    ?)
    0.07
    ,)
    0.07
    Activations Density 0.771%

    No Known Activations