© 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. 33497
    Prev
    Next
    INDEX
    Explanations

    positive and negative signs

    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
    _strlen
    -0.09
     incons
    -0.08
    ISTR
    -0.08
    åıijçĶµéĩı
    -0.08
    çĦļ
    -0.08
    缮çŀª
    -0.08
    -inline
    -0.08
    veranst
    -0.08
    ALLOC
    -0.08
    åı¥è¯Ŀ说
    -0.08
    POSITIVE LOGITS
     negative
    0.10
     Negative
    0.09
    negative
    0.08
    -signed
    0.08
     negatives
    0.08
    è´Ł
    0.08
     positive
    0.08
    Negative
    0.08
     sign
    0.08
    positive
    0.07
    Activations Density 0.028%

    No Known Activations