© 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. 42028
    Prev
    Next
    INDEX
    Explanations

    That followed by verb or possessive

    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
    isode
    -0.08
    ä½łå°Ĩ
    -0.08
    è¿Ļæĺ¯çĶ±äºİ
    -0.08
    æľªæľī
    -0.08
    ç¼ĺçĶ±
    -0.08
     whilst
    -0.08
    ilst
    -0.08
    ename
    -0.07
    umente
    -0.07
    ä¸ĭåIJĮ
    -0.07
    POSITIVE LOGITS
    æĥ³åĪ°è¿ĻéĩĮ
    0.07
    åĨįçľĭçľĭ
    0.07
    ellaneous
    0.06
    笤
    0.06
     is
    0.06
     adalah
    0.06
     an
    0.06
    å¦Ĥæŀľè¢«
    0.06
     ëĺIJíķľ
    0.06
    IMA
    0.06
    Activations Density 0.008%

    No Known Activations