© 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. 88959
    Prev
    Next
    INDEX
    Explanations

    Code/technical writing

    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
    ç«Ł
    -0.29
    oming
    -0.26
    å¦ĤæľŁ
    -0.26
    lobs
    -0.25
    rokes
    -0.25
    icits
    -0.25
    æĮ½æķij
    -0.25
     Lamb
    -0.24
    å¾Ĵ
    -0.24
    cludes
    -0.24
    POSITIVE LOGITS
    çļĦåİŁåĪĻ
    0.28
    idor
    0.28
    anner
    0.27
    çļĦæĦıè§ģ
    0.26
    å¥Ĺ
    0.26
    èĮĥåĽ´åĨħ
    0.25
    åĮºåŁŁåĨħ
    0.25
    çĬ¶æĢģä¸ĭ
    0.24
    è®Ńç»ĥ
    0.24
    åºĹåĨħ
    0.24
    Activations Density 23.425%

    No Known Activations