© 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. 12-TRANSCODER-HP
    7. 22923
    Prev
    Next
    INDEX
    Explanations

    academic/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coordinated
    -0.26
     concurrent
    -0.26
    reek
    -0.25
     merit
    -0.25
    主ä¸ļ
    -0.25
     cork
    -0.24
     concurrently
    -0.24
     captive
    -0.24
     parties
    -0.24
    æĥħåĨµä¸ĭ
    -0.24
    POSITIVE LOGITS
    éĤ£æ®µ
    0.27
    人æīį
    0.27
    _initializer
    0.26
     zwy
    0.25
     <![
    0.25
    sse
    0.25
    angi
    0.25
    malink
    0.25
     lifted
    0.25
    åĽł
    0.24
    Activations Density 0.001%

    No Known Activations