© 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. 40642
    Prev
    Next
    INDEX
    Explanations

    Lee

    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
    说ä»Ģä¹Ī
    -0.33
    ulk
    -0.26
    eurs
    -0.26
    è¿ĺåİŁ
    -0.26
    æĢİä¹Īåģļ
    -0.26
    -case
    -0.25
    åıĤ
    -0.25
    åĩºåİĤ
    -0.25
    uito
    -0.24
    ortal
    -0.24
    POSITIVE LOGITS
    Rx
    0.31
    ä¸ĭ次
    0.26
    боÑĤ
    0.25
    .Enqueue
    0.25
    anca
    0.25
     indicating
    0.24
    ä¸Ĭ次
    0.24
    Rp
    0.24
     specified
    0.23
    ãģ¡ãĤĩãģĨ
    0.23
    Activations Density 0.510%

    No Known Activations