© 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. 108054
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    ono
    -0.29
    èĥĨ
    -0.27
     roma
    -0.27
    nings
    -0.27
     daring
    -0.26
    oro
    -0.25
     Hot
    -0.25
    velope
    -0.25
    /conf
    -0.24
    allest
    -0.24
    POSITIVE LOGITS
    Of
    0.29
    arness
    0.29
    oint
    0.26
    èħº
    0.26
    ToString
    0.26
    аÐ
    0.26
    AtIndex
    0.26
    æĢİä¹Īçľĭ
    0.25
    åģİ
    0.25
    ometers
    0.25
    Activations Density 1.551%

    No Known Activations