© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16959
    Prev
    Next
    INDEX
    Explanations

    removal or deletion of items

    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
    롬
    -0.07
    ax
    -0.07
    çĺ
    -0.07
    èµ·åIJį
    -0.06
    éļĶçĿĢ
    -0.06
    pital
    -0.06
    ForResult
    -0.06
    usercontent
    -0.06
    alur
    -0.06
    nett
    -0.06
    POSITIVE LOGITS
     removal
    0.13
    移éĻ¤
    0.12
    ToRemove
    0.12
     Removal
    0.12
    æĪĸåĪłéĻ¤
    0.11
     deletion
    0.11
    ToDelete
    0.11
    _remove
    0.11
     deleting
    0.11
     remove
    0.11
    Activations Density 0.151%

    No Known Activations