© 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. 23956
    Prev
    Next
    INDEX
    Explanations

    novelists names Jamie McCade Turner

    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
    -0.08
    主人åħ¬
    -0.07
     favorable
    -0.06
    ãĢħ
    -0.06
     "
    -0.06
    ä¸Ĭè¿°
    -0.06
    /
    -0.06
    ä¸įèµ·
    -0.06
     (
    -0.06
     leftist
    -0.06
    POSITIVE LOGITS
    å°ıä¸ĥ
    0.09
    റി
    0.08
    rael
    0.08
    âĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģ
    0.08
    amarin
    0.08
    è§Ħ模æľĢ大
    0.08
    kao
    0.08
    æķĽ
    0.08
    âĺħâĺħ
    0.08
    oir
    0.08
    Activations Density 0.147%

    No Known Activations