© 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. 21770
    Prev
    Next
    INDEX
    Explanations

    proof by induction

    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
    éĢĨ天
    -0.08
    ERSIST
    -0.08
    slashes
    -0.08
    ä¹ħçļĦ
    -0.07
    ecast
    -0.07
    ataire
    -0.07
    ittance
    -0.07
    æŀī
    -0.07
    èĶµ
    -0.07
    Insensitive
    -0.07
    POSITIVE LOGITS
     progress
    0.07
    è¡Ķæİ¥
    0.07
     sufficient
    0.07
     contingent
    0.07
     recurs
    0.07
     footh
    0.07
     subst
    0.07
     conditioned
    0.07
    è¿Ľåº¦
    0.07
     enough
    0.07
    Activations Density 0.007%

    No Known Activations