© 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. 25725
    Prev
    Next
    INDEX
    Explanations

    conditional branches

    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
    acher
    -0.10
     Baron
    -0.07
    amad
    -0.07
     Peer
    -0.06
    ycz
    -0.06
     QU
    -0.06
     K
    -0.06
     peer
    -0.06
    cht
    -0.06
    åIJĮåı°
    -0.06
    POSITIVE LOGITS
    å¿ħçĦ¶æĺ¯
    0.12
    .must
    0.10
    åıªèĥ½æĺ¯
    0.10
    ecessarily
    0.09
    å¿ħå®ļ
    0.09
    ä¸Ģå®ļæĺ¯
    0.09
    å¿ħé¡»æĺ¯
    0.09
    å¿ħçĦ¶
    0.08
    leih
    0.08
    çļĦåĶ¯ä¸Ģ
    0.08
    Activations Density 0.033%

    No Known Activations