© 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. 108303
    Prev
    Next
    INDEX
    Explanations

    Code-related 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
    åħĪ导
    -0.29
    nik
    -0.27
    pile
    -0.27
     daily
    -0.27
     smirk
    -0.26
    osal
    -0.25
    nite
    -0.25
     nightly
    -0.25
    ework
    -0.25
    encion
    -0.25
    POSITIVE LOGITS
    uso
    0.26
     synchronized
    0.26
    交ä»ĺ
    0.25
    .wrap
    0.24
    ocities
    0.24
     divide
    0.24
    Er
    0.24
    身å¿ĥ
    0.24
    æĹĭ
    0.24
     Deliver
    0.23
    Activations Density 1.013%

    No Known Activations