© 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. 88872
    Prev
    Next
    INDEX
    Explanations

    Code/data snippets

    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
    awy
    -0.28
    è¶Ł
    -0.27
    èijŃ
    -0.27
    åijĬè¯ī她
    -0.26
     suspense
    -0.26
    roller
    -0.25
    erval
    -0.25
    ä»Ģä¹Īæĺ¯
    -0.24
     ngũ
    -0.24
    erk
    -0.24
    POSITIVE LOGITS
    æĬĦ
    0.30
    -export
    0.29
    æĭįçħ§
    0.28
    æķij
    0.27
    é¢Ī
    0.27
     Export
    0.27
    contra
    0.26
    éĺ²èĮĥ
    0.26
    _EXPORT
    0.26
    TemplateName
    0.26
    Activations Density 23.766%

    No Known Activations