© 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. 62533
    Prev
    Next
    INDEX
    Explanations

    explanation request

    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
    ÅĤow
    -0.08
    wali
    -0.07
    对åı£
    -0.07
    å²Ń
    -0.07
    ĵĴ
    -0.07
    ult
    -0.07
     ìłķê·ľ
    -0.07
    Einst
    -0.07
    zeichnungen
    -0.06
    ä¸įè§ī
    -0.06
    POSITIVE LOGITS
    çIJĨçĶ±
    0.12
     explanation
    0.12
     explanations
    0.11
    åħ¶åİŁåĽł
    0.11
    解éĩĬ
    0.10
     explanatory
    0.10
     Explanation
    0.10
     reasons
    0.10
     reasoning
    0.10
    çļĦ解éĩĬ
    0.10
    Activations Density 0.064%

    No Known Activations