© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30111
    Prev
    Next
    INDEX
    Explanations

    mailbox, clamp, parts, Model, experiments

    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
    èĪįå¾Ĺ
    -0.07
    è°¤
    -0.07
    oust
    -0.06
    quam
    -0.06
    째
    -0.06
    ckt
    -0.06
    æŀ·
    -0.06
    arla
    -0.06
     تÙĦÙģ
    -0.06
    çĶ²çŃī
    -0.06
    POSITIVE LOGITS
    icu
    0.08
    اصÙĦ
    0.07
    ivi
    0.07
    ãĥĥãĥĶãĥ³ãĤ°
    0.07
    ettino
    0.07
    itom
    0.06
    å¿ĹæĪIJ
    0.06
    æĺĨ
    0.06
    IVI
    0.06
    itori
    0.06
    Activations Density 0.036%

    No Known Activations