© 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. 88486
    Prev
    Next
    INDEX
    Explanations

    source code

    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
    纪
    -0.27
    vet
    -0.25
    æĹłæ³ķ
    -0.25
    Tu
    -0.25
     postfix
    -0.24
    sing
    -0.24
    åĮĸçļĦ
    -0.24
    ýt
    -0.24
    éĺ²å¾¡
    -0.24
    ub
    -0.24
    POSITIVE LOGITS
    icum
    0.27
    .DataTable
    0.26
    vik
    0.26
     CFR
    0.25
    æ··æ·Ĩ
    0.25
    åıłåĬł
    0.23
     hamm
    0.23
    gradation
    0.23
     excit
    0.23
     midpoint
    0.23
    Activations Density 1.086%

    No Known Activations