© 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. 107553
    Prev
    Next
    INDEX
    Explanations

    Word and term definitions

    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
    éĴį
    -0.28
    @register
    -0.25
     weg
    -0.25
    tle
    -0.24
    oded
    -0.24
    heit
    -0.24
    ader
    -0.23
    åıĤ
    -0.23
    讹
    -0.23
    Scott
    -0.23
    POSITIVE LOGITS
    pong
    0.29
    jeta
    0.28
    åĬ¨
    0.27
     Blonde
    0.27
     Trial
    0.26
    Trial
    0.25
     trials
    0.25
    æŶéĹ´ä¸º
    0.24
    -SA
    0.24
    tdown
    0.24
    Activations Density 14.282%

    No Known Activations