© 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. 46131
    Prev
    Next
    INDEX
    Explanations

    for purposes

    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
    atap
    -0.07
    adari
    -0.07
    è§Ħå¾ĭ
    -0.07
    è§Ħå¾ĭçļĦ
    -0.06
    relude
    -0.06
    ä½Ļåħī
    -0.06
    å½ĵä¸ŃçļĦ
    -0.06
    饥
    -0.06
    è¨Ģä¹ĭ
    -0.06
    对ä¼ģä¸ļ
    -0.06
    POSITIVE LOGITS
     purposes
    0.08
    çī¹å®ļçļĦ
    0.08
     Zwecke
    0.08
    ÙĦاÙĦØ©
    0.08
    åķĨä¸ļçĶ¨éĢĶ
    0.08
    antro
    0.07
    çī¹å®ļ
    0.07
     пÑĢедÑģÑĤоÑı
    0.07
     each
    0.07
    สมà¸Ħวร
    0.07
    Activations Density 0.440%

    No Known Activations