© 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. 63554
    Prev
    Next
    INDEX
    Explanations

    academic/theoretical texts

    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
    orate
    -0.27
    ceptor
    -0.26
    PageIndex
    -0.26
     baÅŁÄ±na
    -0.26
    =key
    -0.26
    èģ¯åIJĪ
    -0.25
    師
    -0.25
     coolest
    -0.25
     Rebels
    -0.24
    èī¯å¥½
    -0.23
    POSITIVE LOGITS
    对ä»ĺ
    0.27
    adia
    0.26
     st
    0.26
     concentrated
    0.26
    let
    0.26
    /vnd
    0.25
    åºĶ对
    0.25
    och
    0.25
    XObject
    0.24
     pcs
    0.24
    Activations Density 48.392%

    No Known Activations