© 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. 24327
    Prev
    Next
    INDEX
    Explanations

    neural network layers

    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
     Enumeration
    -0.09
    Enumeration
    -0.09
    åĩ«
    -0.08
     enumerator
    -0.08
     cad
    -0.08
    geom
    -0.07
    undu
    -0.07
    让çĶŁæ´»
    -0.07
    .readString
    -0.07
    abend
    -0.07
    POSITIVE LOGITS
     trainable
    0.09
    relu
    0.08
     neural
    0.08
     Neural
    0.08
     neuron
    0.08
     neurons
    0.07
     softmax
    0.07
     outputs
    0.07
    ä¸Ĭ课
    0.07
    麻éĽĢ
    0.07
    Activations Density 0.058%

    No Known Activations