© 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. 31172
    Prev
    Next
    INDEX
    Explanations

    parental biological relationships

    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
     плоÑīа
    -0.07
    ãĤ®ãĥ¥
    -0.07
    ØŃÙħد
    -0.07
    ä¸İåıijå±ķ
    -0.07
    echos
    -0.07
    Wunused
    -0.06
    éļĶ
    -0.06
    iu
    -0.06
    &A
    -0.06
    ilst
    -0.06
    POSITIVE LOGITS
    Æ¡i
    0.09
    åıªæıIJä¾Ľ
    0.09
    iefert
    0.08
    è´¡çĮ®
    0.08
    -provider
    0.07
    æĸ½åĬł
    0.07
    OrDefault
    0.07
    -contrib
    0.07
    asikan
    0.07
    வரà¯į
    0.07
    Activations Density 0.012%

    No Known Activations