© 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. 19-TRANSCODER-HP
    7. 8181
    Prev
    Next
    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parable
    -0.34
    Advisor
    -0.26
    ç³ĸå°¿
    -0.25
    [opt
    -0.25
    ewise
    -0.24
    AVIS
    -0.24
    keit
    -0.24
     Marc
    -0.24
    Advice
    -0.24
    iche
    -0.23
    POSITIVE LOGITS
    çķ¥
    0.30
    tracks
    0.29
    åĨĹ
    0.26
    compat
    0.25
    ضا
    0.25
    åĪĿ级
    0.25
    çķ
    0.24
    TRACK
    0.24
    èİ·èĥľ
    0.24
     Rocks
    0.24
    Activations Density 0.006%

    No Known Activations