© 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. 89804
    Prev
    Next
    INDEX
    Explanations

    record

    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
    füh
    -0.28
    æľ¬ç«Ļ
    -0.28
    kte
    -0.28
    ndo
    -0.26
    acock
    -0.26
    fits
    -0.26
    /Foundation
    -0.25
    dives
    -0.25
    çĪª
    -0.25
    achu
    -0.25
    POSITIVE LOGITS
    ään
    0.28
    â¬ħ
    0.28
    lu
    0.28
    éĢĤæŶ
    0.28
     maç
    0.27
    âĨIJ
    0.27
     wh
    0.27
     unt
    0.26
    (reason
    0.26
     oriented
    0.25
    Activations Density 2.645%

    No Known Activations