© 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. 7780
    Prev
    Next
    INDEX
    Explanations

    bullet points, notes, or lists

    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
    rost
    -0.08
    æ¸
    -0.07
    inov
    -0.07
    alon
    -0.07
    çĻ¾ç§ij
    -0.07
    "value
    -0.07
    urable
    -0.07
    ekar
    -0.06
    éĤĤéĢħ
    -0.06
    èĥ½ä¸įèĥ½
    -0.06
    POSITIVE LOGITS
    uis
    0.07
    ç²ķ
    0.06
    éĽĢè·ĥ
    0.06
     дÑı
    0.06
     вза
    0.06
     reven
    0.06
     campan
    0.06
     scre
    0.06
    ì£Ħ
    0.06
     Carn
    0.06
    Activations Density 0.004%

    No Known Activations