© 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. 88315
    Prev
    Next
    INDEX
    Explanations

    biological, chemical processes

    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
    éĴ¹
    -0.30
    olvable
    -0.28
     Quantity
    -0.27
    空æ°Ķè´¨éĩı
    -0.27
    éĵĹ
    -0.26
     Edge
    -0.25
     Ki
    -0.25
     Culture
    -0.25
    Edge
    -0.25
    IBILITY
    -0.25
    POSITIVE LOGITS
    å¤ĦåĪĨ
    0.29
    NDER
    0.29
    uddy
    0.26
    è¯ķè¡Į
    0.26
    ä¸ģ
    0.25
    adge
    0.25
    è¿·æĥij
    0.24
    ä»£æĽ¿
    0.24
     accom
    0.23
    Ven
    0.23
    Activations Density 14.800%

    No Known Activations