© 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. 15567
    Prev
    Next
    INDEX
    Explanations

    another followed by noun

    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
    èī²åĪĹ
    -0.08
    awat
    -0.08
    äºĽä»Ģä¹Ī
    -0.08
    ew
    -0.07
    äºİä¸Ģ
    -0.07
    ificante
    -0.07
    以ä¸ĭåĨħ容
    -0.07
    iley
    -0.07
    ãģĺãĤģãģ¦
    -0.07
    stant
    -0.07
    POSITIVE LOGITS
     approach
    0.09
    æĢĿè·¯
    0.08
    ÑĢÑĸм
    0.07
    æĥ³æ³ķ
    0.07
    =”
    0.07
    appro
    0.07
    frog
    0.07
     grouping
    0.06
     ìĥĿê°ģ
    0.06
    åĽŀäºĭ
    0.06
    Activations Density 0.003%

    No Known Activations