© 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. 20994
    Prev
    Next
    INDEX
    Explanations

    focused light optics

    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
    æī¯
    -0.08
    .SDK
    -0.08
    飧
    -0.07
    亲
    -0.07
    åĨ»
    -0.07
    rido
    -0.07
    æ¶īåıĬçļĦ
    -0.07
    ãĤĴå±ķéĸĭ
    -0.07
    .IsActive
    -0.07
    ationToken
    -0.07
    POSITIVE LOGITS
    æ±ĩèģļ
    0.10
    èģļ
    0.10
     convergence
    0.08
    ä¸įæķ£
    0.08
     conver
    0.08
    èģļçĦ¦
    0.08
    èĥ½å°Ĩ
    0.08
     cone
    0.08
    èĥ½æĬĬ
    0.08
    éĽĨä¸Ń
    0.08
    Activations Density 0.016%

    No Known Activations