© 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. 33540
    Prev
    Next
    INDEX
    Explanations

    action followed by "to"

    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
    ãģ¾ãģ¾
    -0.08
    人们对äºİ
    -0.08
    apons
    -0.08
    ikiran
    -0.07
    дзе
    -0.07
     gern
    -0.07
    برة
    -0.07
    äºŁå¾ħ
    -0.07
    å±ĭãģķãĤĵ
    -0.06
    ÙĥÙħ
    -0.06
    POSITIVE LOGITS
     to
    0.21
     να
    0.16
    à¸Ĺีà¹Īà¸Īะ
    0.15
     sÄĥ
    0.13
     Äijá»ĥ
    0.13
    ToSend
    0.11
    ToAdd
    0.11
     ׾×Ķ×Ļ×ķת
    0.11
    ToDelete
    0.10
    ToUpdate
    0.10
    Activations Density 0.967%

    No Known Activations