© 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. 89995
    Prev
    Next
    INDEX
    Explanations

    Reports and article snippets

    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
    sist
    -0.31
    ibur
    -0.29
     desperate
    -0.26
    éĤ¸
    -0.26
    -have
    -0.25
    ä¸įåĪ©
    -0.25
    tractor
    -0.25
    chg
    -0.24
    -fly
    -0.24
    istle
    -0.24
    POSITIVE LOGITS
    łéĻ¤
    0.28
    bel
    0.28
    layan
    0.27
    ek
    0.27
     else
    0.26
     اÙĦÙĨÙĪع
    0.25
    .sm
    0.25
    åĪĿ
    0.25
     spirit
    0.25
    åŀĭ
    0.24
    Activations Density 37.262%

    No Known Activations