© 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. 12-TRANSCODER-HP
    7. 22654
    Prev
    Next
    INDEX
    Explanations

    place names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľºéĿ¢
    -0.28
    çļĩ
    -0.26
    [prop
    -0.25
    itelist
    -0.25
    äºİæĺ¯
    -0.25
     Hóa
    -0.24
     Architect
    -0.24
    ä¾Ŀçħ§
    -0.24
    .Broadcast
    -0.24
    æ°Ĺ
    -0.23
    POSITIVE LOGITS
    ä¸ĬçıŃ
    0.28
    erson
    0.27
     relations
    0.25
    usher
    0.25
    gles
    0.25
     programme
    0.25
    moid
    0.25
    loop
    0.24
    æīĭä¸Ĭ
    0.24
    uilt
    0.24
    Activations Density 0.009%

    No Known Activations