© 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. 23-TRANSCODER-HP
    7. 24851
    Prev
    Next
    INDEX
    Explanations

    DJ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    |`↵
    -0.28
    å®īå®ģ
    -0.27
    |}↵
    -0.26
    é«ĺ级
    -0.25
    容è²Į
    -0.24
    åľ°åĿª
    -0.24
    subpackage
    -0.24
     amp
    -0.24
    oref
    -0.23
     estad
    -0.23
    POSITIVE LOGITS
     "..
    0.28
    tee
    0.25
    ãģ¬
    0.24
    kn
    0.24
    顶端
    0.24
    plorer
    0.24
     fri
    0.24
    unes
    0.23
    ien
    0.23
    ç½ħ
    0.23
    Activations Density 0.011%

    No Known Activations