© 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. 30827
    Prev
    Next
    INDEX
    Explanations

    see, start, configure, stress, Mount

    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
    <|fim_suffix|>
    -0.07
    æ¯ıåħ¬æĸ¤
    -0.07
    æĤ¯
    -0.07
    SR
    -0.07
    west
    -0.07
    åħĪçĶŁ
    -0.07
    ẽ
    -0.07
    kamp
    -0.07
    ��
    -0.06
    हà¥ģ
    -0.06
    POSITIVE LOGITS
    è§ģ
    0.10
    åıĤè§ģ
    0.08
    see
    0.08
     siehe
    0.08
     See
    0.08
    è¦ĭ
    0.07
    LOSE
    0.07
     -,
    0.07
     SEE
    0.07
    igans
    0.07
    Activations Density 0.008%

    No Known Activations