© 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. 64265
    Prev
    Next
    INDEX
    Explanations

    opposite practice

    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
    adr
    -0.08
    æ³°å±±
    -0.08
    zza
    -0.08
    ignty
    -0.07
    _RAW
    -0.07
    æŃ¤èµ·
    -0.07
     underlying
    -0.07
    emer
    -0.07
    DIR
    -0.07
    èį¯çī©
    -0.07
    POSITIVE LOGITS
    åĽ´
    0.08
    éļıåľ°
    0.07
    æľīè´£
    0.07
    åĮħæĭ¬
    0.07
    æ¼ıæĸĹ
    0.07
    å°±è¿ij
    0.07
    èĩ³å°ij
    0.07
    oins
    0.07
    includes
    0.07
    horn
    0.07
    Activations Density 0.007%

    No Known Activations