© 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. 15131
    Prev
    Next
    INDEX
    Explanations

    derivative calculation

    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
    ä¸įå¿į
    -0.07
    бли
    -0.07
    zt
    -0.07
    oodle
    -0.07
    Ģ
    -0.06
     prov
    -0.06
     suf
    -0.06
    ÅĪ
    -0.06
    éĹ®é¢ĺæķ´æĶ¹
    -0.06
     together
    -0.06
    POSITIVE LOGITS
    פש
    0.08
     Hogan
    0.08
    aise
    0.08
    äºīåħĪ
    0.08
    esso
    0.08
    ühl
    0.08
    yla
    0.07
    ij
    0.07
    .Typed
    0.07
    raż
    0.07
    Activations Density 0.004%

    No Known Activations