© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 90044
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     duty
    -0.29
    habit
    -0.27
    bitrary
    -0.26
     attributed
    -0.26
     responsibilities
    -0.24
    egl
    -0.24
    abcdefghijkl
    -0.24
    rÄĻ
    -0.23
    (Attribute
    -0.23
    ustralian
    -0.23
    POSITIVE LOGITS
    .ht
    0.26
    åİŁåĽłä¹ĭä¸Ģ
    0.26
    stell
    0.25
    çİĦ
    0.24
     Wid
    0.24
     marg
    0.24
    ç®Ĺ
    0.24
     manh
    0.23
    èĥ½åľ¨
    0.23
    @test
    0.23
    Activations Density 0.083%

    No Known Activations

    This feature has no known activations.