© 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. 18369
    Prev
    Next
    INDEX
    Explanations

    particular, set, optional, try, homos, responsive, wearing, usually, sizes

    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
    ubil
    -0.08
    æĭĽ
    -0.08
    aina
    -0.08
    udin
    -0.07
     loÃłi
    -0.07
    ecin
    -0.07
    ä¸Ģå¼ı
    -0.07
    broker
    -0.07
    ède
    -0.07
    ç§ĥ
    -0.07
    POSITIVE LOGITS
    çĤ¯
    0.08
    åį³ä¾¿
    0.07
    t
    0.07
    blia
    0.07
     even
    0.07
    åį³ä¾¿å¦ĤæѤ
    0.06
    åį³ä½¿
    0.06
    OMO
    0.06
    NG
    0.06
     Even
    0.06
    Activations Density 0.267%

    No Known Activations