© 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. 88845
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Normalized
    -0.30
    èģĶ社
    -0.29
    assin
    -0.28
     Liberation
    -0.26
     Setup
    -0.25
    -normal
    -0.24
     ör
    -0.24
    locator
    -0.24
    VICE
    -0.24
    rita
    -0.24
    POSITIVE LOGITS
    æĹ©æĹ¥
    0.28
    ä»ĸæĽ¾
    0.28
    icz
    0.28
    swift
    0.27
    <KeyValuePair
    0.26
     quick
    0.26
    bose
    0.26
    æŁĦ
    0.26
    Cached
    0.26
     phantom
    0.26
    Activations Density 33.490%

    No Known Activations