© 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. 40056
    Prev
    Next
    INDEX
    Explanations

    numbers and data

    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
    ä¸Ģç¬Ķ
    -0.28
    å¾Ĺèµ·
    -0.27
    两次
    -0.26
    uali
    -0.26
    æĪ³
    -0.25
    辫
    -0.25
    åıijçİ°
    -0.24
    æĶ¯æĮģåĬĽåº¦
    -0.24
    -support
    -0.24
    åĬłéĢŁ
    -0.24
    POSITIVE LOGITS
    æĸĹ
    0.27
    ól
    0.25
    xmm
    0.25
    .DropDown
    0.25
    ilib
    0.24
    uppies
    0.24
    åħĦ
    0.24
    anken
    0.24
    ˣ
    0.24
    erview
    0.24
    Activations Density 0.646%

    No Known Activations