© 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. 18633
    Prev
    Next
    INDEX
    Explanations

    proof: or let's show

    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
    WithError
    -0.08
    onex
    -0.08
     representative
    -0.08
    å¼ģ
    -0.08
    represented
    -0.08
    represent
    -0.08
     discret
    -0.08
    代表
    -0.07
     represents
    -0.07
     representa
    -0.07
    POSITIVE LOGITS
    迫使
    0.11
    éĢ¼
    0.10
     stronger
    0.09
    éĢ¼è¿«
    0.08
     forced
    0.08
    强åĪ¶
    0.08
    强迫
    0.08
     contradiction
    0.08
     forcing
    0.08
    强
    0.08
    Activations Density 0.031%

    No Known Activations