© 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. 89359
    Prev
    Next
    INDEX
    Explanations

    Mentions of time periods

    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
    èĩ¼
    -0.29
     today
    -0.27
    elly
    -0.25
    çļĦè¿ĽæŃ¥
    -0.25
    exels
    -0.25
    oder
    -0.25
     Bib
    -0.25
    owler
    -0.25
     internals
    -0.24
    ез
    -0.24
    POSITIVE LOGITS
    unsch
    0.33
    åľ³
    0.27
    imation
    0.26
    æľĭåıĭ
    0.25
    SCO
    0.25
    æīĢåľ¨
    0.25
    icum
    0.24
    duplicate
    0.24
    loo
    0.23
    å±ķè§Ī
    0.23
    Activations Density 5.284%

    No Known Activations