© 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. 88529
    Prev
    Next
    INDEX
    Explanations

    Code or text 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
     convertible
    -0.27
    *
    -0.27
    templates
    -0.25
    ieee
    -0.24
     inf
    -0.24
     hen
    -0.24
    æ··åĩĿ
    -0.24
     won
    -0.23
    <script
    -0.23
    Templates
    -0.23
    POSITIVE LOGITS
    ivor
    0.30
    fant
    0.27
     grew
    0.27
    æĬĬè¿ĻäºĽ
    0.26
    nard
    0.25
    EMY
    0.25
    ês
    0.24
    gó
    0.24
    برÙĬ
    0.24
     поÑĢ
    0.24
    Activations Density 56.447%

    No Known Activations