© 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. 25-TRANSCODER-HP
    7. 109024
    Prev
    Next
    INDEX
    Explanations

    chatbot / coding text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĽ´å¥½çļĦ
    -0.29
    ngth
    -0.29
    úb
    -0.28
    /Gate
    -0.27
    .liferay
    -0.27
    .DEFINE
    -0.25
    ktor
    -0.25
    teenth
    -0.25
    ply
    -0.24
    kiem
    -0.24
    POSITIVE LOGITS
     or
    0.41
     The
    0.37
     None
    0.35
     It
    0.31
     Or
    0.30
     In
    0.29
     Conditions
    0.29
     m
    0.28
     Its
    0.28
     Car
    0.28
    Activations Density 0.898%

    No Known Activations