© 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. 23748
    Prev
    Next
    INDEX
    Explanations

    away

    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
    bond
    -0.29
    tr
    -0.28
    extr
    -0.26
    lös
    -0.26
    å±ŀäºİ
    -0.26
    ign
    -0.26
    otor
    -0.25
    åĪ«çļĦ
    -0.25
    åŃĺåľ¨
    -0.25
     gating
    -0.24
    POSITIVE LOGITS
    æµģåħ¥
    0.29
     AraÅŁtırma
    0.27
     crossorigin
    0.26
    velle
    0.25
    alley
    0.25
    æĪijä¼ļ
    0.24
    ANTLR
    0.24
     argc
    0.23
    .access
    0.23
     terminated
    0.23
    Activations Density 0.046%

    No Known Activations