© 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. 88426
    Prev
    Next
    INDEX
    Explanations

    technical/abstract

    np_max-act · gemini-2.0-flash
    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
    ercul
    -0.29
    CATEGORY
    -0.27
    åĢ¦
    -0.26
    ä¸ĢåłĨ
    -0.25
    -Mart
    -0.25
    è¿ĩç¨ĭå½ĵä¸Ń
    -0.25
    fx
    -0.25
    imar
    -0.24
    æīįèĥ½å¤Ł
    -0.24
    .gs
    -0.24
    POSITIVE LOGITS
     chế
    0.27
     æĪĸ
    0.26
    社
    0.26
    [](
    0.25
     ton
    0.25
     eller
    0.25
    å¼Ģæľº
    0.25
    èĢĴ
    0.25
     below
    0.24
     NAMES
    0.24
    Activations Density 2.255%

    No Known Activations