© 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. 27219
    Prev
    Next
    INDEX
    Explanations

    "one of", "want to", "several rural"

    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
    çĴŀ
    -0.08
    uwd
    -0.08
    ÙĦاÙĭ
    -0.08
    odr
    -0.08
    è½»çĽĪ
    -0.08
    ÙĦاÙĦ
    -0.07
    cliffe
    -0.07
    ÙģÙĬÙĨ
    -0.07
    haft
    -0.07
    åħĨ
    -0.07
    POSITIVE LOGITS
    agin
    0.06
    æĬ½çĥŁ
    0.06
    çŃīæľīåħ³
    0.06
    é¢ĩå¤ļ
    0.06
    æĥľ
    0.06
    ä¸ŃçļĦä¸Ģç§į
    0.06
    转èĩª
    0.06
     недо
    0.06
    èĶ¼
    0.06
    åıijå±ķ壮大
    0.06
    Activations Density 0.002%

    No Known Activations