© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89617
    Prev
    Next
    INDEX
    Explanations

    technical/programming contexts

    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
    iez
    -0.24
    (sent
    -0.23
    訾
    -0.23
    obia
    -0.23
    epoch
    -0.23
    GREE
    -0.23
     (_.
    -0.22
    ueblo
    -0.22
    ÎĪ
    -0.22
    æĪIJ
    -0.22
    POSITIVE LOGITS
    ä¸ªé¡¹çĽ®
    0.28
    å½»
    0.27
     WANT
    0.26
     GA
    0.26
    minor
    0.26
    poster
    0.26
    htags
    0.25
    ivated
    0.25
    çļĦ女åĦ¿
    0.25
    endif
    0.25
    Activations Density 22.000%

    No Known Activations