© 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. 43396
    Prev
    Next
    INDEX
    Explanations

    $$ followed by text

    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
    aten
    -0.07
    и
    -0.07
     vs
    -0.06
    tls
    -0.06
     algo
    -0.06
    sex
    -0.06
    apat
    -0.06
    hone
    -0.06
    als
    -0.06
    ÙĦاء
    -0.06
    POSITIVE LOGITS
    åĭĩå¾Ģ缴åīį
    0.09
    å®ĥåħ·æľī
    0.09
    å®ĥæľī
    0.08
    ciu
    0.08
    身临åħ¶å¢ĥ
    0.08
    解ç¦ģ
    0.08
    æį¢è¨Ģä¹ĭ
    0.08
     consort
    0.08
    æīĭæľºç«Ļ
    0.08
    缸è¾ħ缸æĪIJ
    0.07
    Activations Density 0.003%

    No Known Activations