© 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. 39951
    Prev
    Next
    INDEX
    Explanations

    separators and conjunctions

    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
     originals
    -0.29
    eday
    -0.28
    _accessible
    -0.28
     replicated
    -0.28
     pdf
    -0.27
     italia
    -0.27
    jom
    -0.26
     finale
    -0.26
    ubb
    -0.26
    Powered
    -0.25
    POSITIVE LOGITS
    åľ¨åĮĹ京
    0.26
    æĭī
    0.26
    ho
    0.25
     pulling
    0.25
     lay
    0.25
    åħĪ天
    0.24
    è¿«
    0.24
     th
    0.24
    venting
    0.24
    è£Ĥ
    0.24
    Activations Density 0.277%

    No Known Activations