© 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. 3119
    Prev
    Next
    INDEX
    Explanations

    "little pig" saw

    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
    èī°
    -0.08
    å°ıå¿ĥ翼翼
    -0.08
    åĬªåĬĽåľ°
    -0.08
    å°ıå¿ĥç¿¼ç¿¼åľ°
    -0.07
     tries
    -0.07
    fails
    -0.07
    æīĭå¿Ļ
    -0.07
    oot
    -0.07
    åĵĨ
    -0.07
     fails
    -0.07
    POSITIVE LOGITS
    ä»İ容
    0.11
    å¹³çŃīçļĦ
    0.08
    游åĪĥæľīä½Ļ
    0.08
    reverse
    0.08
    èĹIJ
    0.08
     contempt
    0.08
    assen
    0.08
     brilliantly
    0.08
    å·§å¦ĻçļĦ
    0.08
     equality
    0.08
    Activations Density 0.154%

    No Known Activations