© 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. 90181
    Prev
    Next
    INDEX
    Explanations

    Technical/code explanations

    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
     Omn
    -0.27
     Judgment
    -0.26
     neither
    -0.25
     Inf
    -0.25
     pratic
    -0.25
     Body
    -0.25
    _Int
    -0.25
    пÑĢод
    -0.25
    à°¦
    -0.25
     Infer
    -0.24
    POSITIVE LOGITS
    èħ¥
    0.28
    éĺ¡
    0.28
    rf
    0.26
    acer
    0.25
    ieten
    0.25
    CRET
    0.24
    ModelProperty
    0.24
    æ´¥
    0.24
    ä½ľåĩºäºĨ
    0.24
    è¾ĵç»Ļ
    0.24
    Activations Density 46.884%

    No Known Activations