© 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. 14-TRANSCODER-HP
    7. 40479
    Prev
    Next
    INDEX
    Explanations

    Prices and retail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gm
    -0.29
    atto
    -0.29
    ATAR
    -0.28
    ÇĶ
    -0.27
    -sheet
    -0.27
    itsu
    -0.26
    .Program
    -0.25
    审计
    -0.25
    ä»Ĺ
    -0.25
    جة
    -0.25
    POSITIVE LOGITS
     royalty
    0.28
    dens
    0.26
    onne
    0.26
     cle
    0.25
     kok
    0.25
    åĬłä¸Ĭ
    0.25
    ä¹ĸä¹ĸ
    0.24
    à¹Ħล
    0.24
    bps
    0.24
    追
    0.24
    Activations Density 0.415%

    No Known Activations