© 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. 23051
    Prev
    Next
    INDEX
    Explanations

    appreciate

    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
    ework
    -0.26
    avr
    -0.25
    ि
    -0.25
    é¦ĸåıij
    -0.24
     Ho
    -0.24
     shareholder
    -0.23
     Adopt
    -0.23
    æĦŁæ¿Ģ
    -0.23
    cascade
    -0.23
     resent
    -0.23
    POSITIVE LOGITS
    ères
    0.28
     Klaus
    0.28
    éħįæĸĻ
    0.27
    å¹´é¾Ħ段
    0.25
     Strait
    0.25
    erals
    0.25
    ç¢İçīĩ
    0.25
    axies
    0.25
    icals
    0.25
    ellschaft
    0.24
    Activations Density 0.027%

    No Known Activations