© 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. 31326
    Prev
    Next
    INDEX
    Explanations

    database hosting

    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
    _lineno
    -0.09
    —.
    -0.07
    DEFINE
    -0.07
    黯çĦ¶
    -0.07
    ëıĦë¡ľ
    -0.06
    å®īåħ¨éĺ²æĬ¤
    -0.06
    森
    -0.06
    åIJij被åijĬ
    -0.06
    èµĦæºIJç½ij
    -0.06
     ::=
    -0.06
    POSITIVE LOGITS
    好åij¢
    0.07
    weiten
    0.07
    ach
    0.07
    çŃīçī¹æ®Ĭ
    0.07
    astos
    0.07
    ä¸įæĹ©
    0.07
    uvent
    0.06
    ะ
    0.06
    ola
    0.06
    é©Ń
    0.06
    Activations Density 0.001%

    No Known Activations