© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44831
    Prev
    Next
    INDEX
    Explanations

    compensating for

    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
    -0.11
    enberg
    -0.08
    ender
    -0.07
    hood
    -0.07
    à¹Ģà¸ģิà¸Ļà¹Ħà¸Ľ
    -0.07
    iscard
    -0.06
    elihood
    -0.06
    ambul
    -0.06
    vore
    -0.06
    finity
    -0.06
    POSITIVE LOGITS
    aneous
    0.09
    ively
    0.09
    -UA
    0.09
    ÑģÑı
    0.09
    èµ·è§ģ
    0.09
    ably
    0.08
    ionate
    0.08
    ulate
    0.08
     Agung
    0.08
    aign
    0.08
    Activations Density 0.007%

    No Known Activations