© 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. 24898
    Prev
    Next
    INDEX
    Explanations

    later, then add

    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
    veu
    -0.07
    æѤåīį
    -0.06
    uis
    -0.06
    åľ¨æĪijåĽ½
    -0.06
     âĶľ
    -0.06
    èĵĦ
    -0.06
     therein
    -0.06
    çĬ¶åĨµ
    -0.06
     din
    -0.06
    events
    -0.06
    POSITIVE LOGITS
    itta
    0.09
     кÑĥÑĢÑĤ
    0.07
    ç¬ij
    0.07
    RY
    0.07
    æħ·
    0.07
    壮
    0.07
    åĽŀ乡
    0.07
    ]int
    0.07
    eam
    0.07
     targ
    0.07
    Activations Density 0.012%

    No Known Activations