© 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. 25031
    Prev
    Next
    INDEX
    Explanations

    before crash

    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
     impun
    -0.08
     Moraes
    -0.07
     McL
    -0.07
    amani
    -0.07
    HE
    -0.07
    ¹Ħ
    -0.07
    缴æİ¥æĪĸéĹ´æİ¥
    -0.06
    abil
    -0.06
    åĨįæľī
    -0.06
    unno
    -0.06
    POSITIVE LOGITS
    ry
    0.09
    roh
    0.08
    áŁĤ
    0.07
     pressi
    0.07
    ãĥĥãĤ·ãĥ¥
    0.07
    entar
    0.07
    hto
    0.07
    aghan
    0.07
    天åħĥ
    0.07
    hausen
    0.07
    Activations Density 0.003%

    No Known Activations