© 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. 28430
    Prev
    Next
    INDEX
    Explanations

    dismiss, denying, judgment

    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
    çīĪæĿĥä¸İåħį责声æĺİ
    -0.06
     reck
    -0.06
    çŃĸ
    -0.06
    åħ¶èº«
    -0.06
    åĪĨå¸ĥ
    -0.06
    ischer
    -0.06
    oreal
    -0.06
    åľ¨ç»Ļ
    -0.06
     betrayed
    -0.06
    ÐijолÑĮ
    -0.06
    POSITIVE LOGITS
    驳åĽŀ
    0.10
    ä¸įäºĪåıĹçIJĨ
    0.09
    <|box_end|>
    0.08
    管çIJĨç±»
    0.08
    Validity
    0.08
    æĹłæķĪçļĦ
    0.08
    声ä¸Ń
    0.08
     заÑı
    0.08
    èıģèĭ±
    0.08
     Logical
    0.08
    Activations Density 0.150%

    No Known Activations