© 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. 89432
    Prev
    Next
    INDEX
    Explanations

    Identifying specific things

    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
    woke
    -0.30
    ä¸īä½į
    -0.27
    身
    -0.25
    поÑĤÑĢеб
    -0.25
    rew
    -0.25
    =q
    -0.25
    çļĦéĤ£ä¸Ģ
    -0.25
    propri
    -0.24
    /fw
    -0.24
    è§ĴéĢIJ
    -0.24
    POSITIVE LOGITS
    |
    0.28
    æĭİ
    0.24
    |↵
    0.24
     all
    0.24
    ime
    0.24
     t
    0.24
    ead
    0.23
     Hard
    0.23
     mana
    0.23
     as
    0.23
    Activations Density 22.115%

    No Known Activations