© 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. 30311
    Prev
    Next
    INDEX
    Explanations

    color vision discrimination

    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
    骸
    -0.08
    arca
    -0.07
    åħ¶èº«
    -0.07
    odat
    -0.07
     Ñģко
    -0.07
    .nano
    -0.07
    ambu
    -0.07
     Atom
    -0.06
     stor
    -0.06
    å¾Ħ
    -0.06
    POSITIVE LOGITS
     discrimination
    0.08
    对è§Ĩ
    0.08
    æĹłèī²
    0.08
    åħīè°±
    0.08
    RGB
    0.07
     ÑĨвеÑĤо
    0.07
     Discrim
    0.07
     segreg
    0.07
    æĪij社
    0.07
    èī²ç³»
    0.07
    Activations Density 0.009%

    No Known Activations