© 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. 40612
    Prev
    Next
    INDEX
    Explanations

    Code and technical text

    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
    éĶ¹
    -0.27
    yah
    -0.25
     diam
    -0.25
    apur
    -0.24
    leta
    -0.24
    亮
    -0.24
    acula
    -0.23
    è°ħ
    -0.23
    éĹªéĹª
    -0.23
    ate
    -0.23
    POSITIVE LOGITS
    大çīĩ
    0.31
    ilig
    0.27
    vecs
    0.27
    ranges
    0.26
    sterol
    0.26
    _vectors
    0.26
    åİĺ
    0.25
    ä¸Ģç¬ij
    0.25
    kea
    0.25
    好çľĭçļĦ
    0.24
    Activations Density 0.307%

    No Known Activations