© 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. 40867
    Prev
    Next
    INDEX
    Explanations

    Heat and practitioners

    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
    аÑĤÑĮÑģÑı
    -0.29
    ilon
    -0.28
    eners
    -0.28
    layan
    -0.28
    lingen
    -0.25
    abar
    -0.25
    è¦ģåģļ好
    -0.25
    sdale
    -0.24
    ä¸įæŃ»
    -0.24
    ,proto
    -0.24
    POSITIVE LOGITS
    åĮ¹éħį
    0.29
     reality
    0.26
     entails
    0.26
     pä
    0.24
    Trou
    0.24
    åģıåģı
    0.24
    oya
    0.24
     intake
    0.24
    形容
    0.23
    éĻ·
    0.23
    Activations Density 0.854%

    No Known Activations