© 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. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96589
    Prev
    Next
    INDEX
    Explanations

    test names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åıĹ害人
    -0.33
    ¡°
    -0.29
    jah
    -0.28
    isko
    -0.27
     exposures
    -0.26
     clad
    -0.26
    ç®Ķ
    -0.25
    FAILURE
    -0.24
    ä¹ĭæĥħ
    -0.24
    åĢºæĿĥ人
    -0.24
    POSITIVE LOGITS
     testName
    0.30
    Test
    0.29
     test
    0.29
     Test
    0.28
     Device
    0.27
    ç½ijç«Ļåľ°åĽ¾
    0.27
    outer
    0.26
    -test
    0.26
    -Core
    0.25
    core
    0.25
    Activations Density 0.899%

    No Known Activations