© 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. 50722
    Prev
    Next
    INDEX
    Explanations

    pro day, combine, draft

    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
    nhof
    -0.07
     ferment
    -0.07
    Ø¢Ùħ
    -0.07
     fid
    -0.07
    äng
    -0.07
     Conserv
    -0.07
     remis
    -0.07
    ä¸İæŶ
    -0.06
    泡沫
    -0.06
    æłĵ
    -0.06
    POSITIVE LOGITS
    loch
    0.08
    /ion
    0.08
    èĪªç©ºåħ¬åı¸
    0.08
     Aufbau
    0.07
    éĩĬæĶ¾
    0.07
     electron
    0.07
    çķij
    0.07
     Shield
    0.07
    ockets
    0.07
    èĪ·
    0.07
    Activations Density 0.002%

    No Known Activations