© 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. 108105
    Prev
    Next
    INDEX
    Explanations

    for/of

    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
    (mac
    -0.28
    uem
    -0.28
    饲åħ»
    -0.27
    /repos
    -0.27
    erne
    -0.25
    поÑĩ
    -0.24
    çļĦåŁºç¡Ģ
    -0.24
     rhet
    -0.24
    <<<
    -0.24
    :NS
    -0.24
    POSITIVE LOGITS
     design
    0.29
     tangent
    0.28
     similarly
    0.28
     single
    0.27
    设计
    0.27
    æĥ¬
    0.27
    AGMA
    0.27
     standard
    0.26
     fully
    0.26
    Éij
    0.26
    Activations Density 1.011%

    No Known Activations