© 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. 14668
    Prev
    Next
    INDEX
    Explanations

    naming or defining terms

    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¸įæĶ¾
    -0.08
    èĵĸ
    -0.07
    aeda
    -0.07
    getResponse
    -0.07
    otland
    -0.07
    帷
    -0.06
    getEmail
    -0.06
    ollower
    -0.06
     sqr
    -0.06
    ¹Ħ
    -0.06
    POSITIVE LOGITS
    è§ĦèĮĥçļĦ
    0.09
     naming
    0.09
    åľ°åIJį
    0.09
    åij½åIJį
    0.08
    è§ĦèĮĥ
    0.08
     descriptive
    0.08
    åIJį称
    0.08
     name
    0.08
     formal
    0.08
     compliant
    0.08
    Activations Density 0.012%

    No Known Activations