© 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. 90177
    Prev
    Next
    INDEX
    Explanations

    Digits

    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
    Negative Logits
    ogl
    -0.28
    éĻį
    -0.27
    åı¯ä»¥éĢļè¿ĩ
    -0.26
    LinkId
    -0.26
    bara
    -0.26
    loor
    -0.25
     reunion
    -0.25
    laÅŁma
    -0.25
    éĴĿ
    -0.24
     gode
    -0.24
    POSITIVE LOGITS
    å¿ĥ缮
    0.25
     appealed
    0.25
    (dict
    0.25
    afx
    0.25
    ouched
    0.25
    afia
    0.24
    achat
    0.24
     Dá»ĭch
    0.23
    å¸ĮæľĽèĥ½å¤Ł
    0.23
    (helper
    0.23
    Activations Density 6.450%

    No Known Activations