© 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. 89994
    Prev
    Next
    INDEX
    Explanations

    Text snippets with quotes

    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
    (Key
    -0.28
    ato
    -0.27
    ikal
    -0.25
    à¹Ĥร
    -0.25
    enders
    -0.24
     suk
    -0.24
    顺
    -0.24
    ProductId
    -0.24
     remotely
    -0.24
    åĪ©æ¶¦çİĩ
    -0.24
    POSITIVE LOGITS
     splash
    0.28
    xit
    0.26
    geist
    0.25
    validated
    0.25
    normalized
    0.25
    scaled
    0.25
    orst
    0.25
    å¾Ĺ以
    0.24
     (\
    0.24
     shares
    0.24
    Activations Density 1.606%

    No Known Activations