© 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. 89315
    Prev
    Next
    INDEX
    Explanations

    code

    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
    hek
    -0.33
    qid
    -0.30
    @js
    -0.27
    lek
    -0.26
    èĥĦ
    -0.26
    =w
    -0.25
    ittest
    -0.25
    qm
    -0.25
    beh
    -0.24
     wal
    -0.24
    POSITIVE LOGITS
     keep
    0.28
    ä¸įåģľ
    0.26
     reve
    0.26
     strokeLine
    0.26
    çľĭä»ĸ
    0.26
    emer
    0.25
     headlines
    0.25
     keeps
    0.25
     ern
    0.25
     showAlert
    0.24
    Activations Density 3.592%

    No Known Activations