© 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. 20-TRANSCODER-HP
    7. 141667
    Prev
    Next
    INDEX
    Explanations

    Code and file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     воÑĤ
    -0.27
    åį±å®³
    -0.26
    ousy
    -0.26
    ä¼ĺåĬ¿
    -0.26
    èĸĦ
    -0.26
    phet
    -0.25
    ORB
    -0.25
    obil
    -0.25
     Dover
    -0.25
     ÐĴоÑĤ
    -0.25
    POSITIVE LOGITS
     accordingly
    0.28
    anzi
    0.27
    schlie
    0.25
     sát
    0.24
    åĽłåŃIJ
    0.24
    yre
    0.24
     retain
    0.24
    sch
    0.24
    xdc
    0.24
     protest
    0.24
    Activations Density 1.898%

    No Known Activations