© 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. 24-TRANSCODER-HP
    7. 150325
    Prev
    Next
    INDEX
    Explanations

    Facts, dates, scientific information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åı°å·ŀ
    -0.27
     Presidency
    -0.25
    Prov
    -0.25
    汽油
    -0.25
    .getParam
    -0.24
    æĮģæľīçļĦ
    -0.24
     holdings
    -0.24
     sai
    -0.24
     Capitals
    -0.24
    atti
    -0.24
    POSITIVE LOGITS
    itionally
    0.28
    gere
    0.28
    onas
    0.28
    PX
    0.26
    ieres
    0.25
    bles
    0.25
    enced
    0.24
    ateria
    0.24
    pected
    0.24
     PED
    0.24
    Activations Density 1.041%

    No Known Activations