© 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. 32102
    Prev
    Next
    INDEX
    Explanations

    iv hterT

    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
     Bull
    -0.06
     (
    -0.05
    zl
    -0.05
    atti
    -0.05
    3
    -0.05
    ãģľ
    -0.05
    çľĭä¸Ĭ
    -0.05
    dit
    -0.05
     inherent
    -0.05
     .
    -0.05
    POSITIVE LOGITS
    oulouse
    0.09
    acea
    0.08
    лÑıн
    0.08
     TObject
    0.08
    ousel
    0.08
    ×ķ×ķת
    0.08
     모ë¦Ħ
    0.08
    akarta
    0.08
    å°±æĺ¯åĽłä¸º
    0.08
    ëłĪìĬ¤
    0.08
    Activations Density 0.007%

    No Known Activations