© 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. 25-TRANSCODER-HP
    7. 108704
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¨è¦ĨçĽĸ
    -0.29
    .animate
    -0.28
    inate
    -0.28
    -www
    -0.26
    meth
    -0.26
    nea
    -0.26
    inous
    -0.26
    夼
    -0.26
    æĬĬèĩªå·±
    -0.25
    æķ¢äºİ
    -0.24
    POSITIVE LOGITS
    æŀ«
    0.26
    req
    0.25
    éĽĢ
    0.25
    Steps
    0.25
    steps
    0.25
    ç¦ıå¾·
    0.24
    cdc
    0.24
    éļIJèĶ½
    0.24
     Steps
    0.24
    (...)
    0.23
    Activations Density 1.639%

    No Known Activations