© 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. 130298
    Prev
    Next
    INDEX
    Explanations

    mentions places

    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
    åŁºæķ°
    -0.27
    agh
    -0.26
    iev
    -0.26
    æ´½
    -0.26
     entirety
    -0.26
    iew
    -0.25
    whole
    -0.25
    igest
    -0.24
    å°ıåºĹ
    -0.24
    ergarten
    -0.24
    POSITIVE LOGITS
    éĿ¢åħ·
    0.27
    pra
    0.27
    rocessing
    0.27
    åĤ©
    0.26
    带头人
    0.26
    utron
    0.25
    åĴĮå°ļ
    0.25
    BER
    0.24
    åħĭèݱ
    0.24
    cla
    0.24
    Activations Density 20.115%

    No Known Activations