© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14809
    Prev
    Next
    INDEX
    Explanations

    contrast, but, whereas, works

    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
    çĥģ
    -0.08
     alongside
    -0.07
    extras
    -0.07
     layer
    -0.06
     Zan
    -0.06
    urr
    -0.06
     خر
    -0.06
    chs
    -0.06
    omi
    -0.06
    orges
    -0.06
    POSITIVE LOGITS
    åĶ¯çĭ¬
    0.13
     contrast
    0.12
    缸æ¯Ķä¹ĭä¸ĭ
    0.11
     Whereas
    0.11
     selectively
    0.11
    对æ¯Ķ
    0.11
    åĶ¯æľī
    0.11
    åıªå¯¹
    0.11
     Contrast
    0.11
    Selective
    0.10
    Activations Density 0.123%

    No Known Activations