© 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. 40439
    Prev
    Next
    INDEX
    Explanations

    Code, markup, or unusual writing

    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
    že
    -0.30
    å¼ĢéŨ
    -0.29
    æĺİç¡®äºĨ
    -0.28
    æĦļ
    -0.28
     reve
    -0.28
    izr
    -0.26
    hest
    -0.26
    etus
    -0.26
     pint
    -0.25
    æŁ¥çľĭæĽ´å¤ļ
    -0.24
    POSITIVE LOGITS
    身ä¸Ĭ
    0.27
     duplicates
    0.27
    ecom
    0.26
    aken
    0.25
    åħ¼
    0.25
    lij
    0.25
    åĢį
    0.24
     delivered
    0.24
    aye
    0.23
    egl
    0.23
    Activations Density 0.045%

    No Known Activations