© 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. 88278
    Prev
    Next
    INDEX
    Explanations

    Broad range of topics

    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
     Reform
    -0.26
    ades
    -0.26
    .getSimpleName
    -0.25
    .inst
    -0.25
    gerald
    -0.24
     center
    -0.24
    çĴIJ
    -0.24
     centers
    -0.23
    _visibility
    -0.23
     flashlight
    -0.23
    POSITIVE LOGITS
    á»ģn
    0.26
    éĻªä½ł
    0.26
     Horny
    0.26
    è·³è·ĥ
    0.26
    çĭ¬æľīçļĦ
    0.26
    Į¨
    0.25
    ä¸ĢçĶŁ
    0.25
    pto
    0.25
    ailing
    0.24
     utc
    0.24
    Activations Density 16.104%

    No Known Activations