© 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. 88951
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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
    èĥĮä¸Ĭ
    -0.29
    compatible
    -0.29
    åĵī
    -0.27
    欲
    -0.27
    滩
    -0.26
    æīĢè¬Ĥ
    -0.26
    -compatible
    -0.26
     consist
    -0.25
    çľł
    -0.25
     Finite
    -0.25
    POSITIVE LOGITS
     offered
    0.28
     provided
    0.26
     explained
    0.26
     shed
    0.25
     Owens
    0.25
     ki
    0.24
    ypy
    0.24
    è¾ĩ
    0.24
    izing
    0.23
    åģļå¾Ĺ
    0.23
    Activations Density 23.585%

    No Known Activations