© 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. 40523
    Prev
    Next
    INDEX
    Explanations

    was, were

    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
    éĽĨ
    -0.26
    人éĥ½
    -0.26
     according
    -0.25
    åĿª
    -0.25
    ]+)/
    -0.24
    åľ°æĸ¹æĶ¿åºľ
    -0.24
     compilers
    -0.24
     Thumbnail
    -0.23
    IMS
    -0.23
    åĪĿ
    -0.23
    POSITIVE LOGITS
    ambi
    0.25
    lesh
    0.25
    è¿Ľåľº
    0.25
    å²ģæŶ
    0.25
    ouce
    0.25
    æĮ¥
    0.24
    讥
    0.24
    unde
    0.24
    祸
    0.24
    åĩºåİĤ
    0.23
    Activations Density 1.639%

    No Known Activations