© 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. 130449
    Prev
    Next
    INDEX
    Explanations

    el

    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
     cata
    -0.26
     quarters
    -0.25
    éºĭ
    -0.25
    xcf
    -0.25
    æĹıèĩªæ²»åİ¿
    -0.25
    ukan
    -0.25
    ä¹ĭåĬ¿
    -0.25
    ç¾ģ
    -0.24
    æ¶Īè´¹éľĢæ±Ĥ
    -0.24
    åĪ©äºļ
    -0.24
    POSITIVE LOGITS
    _HEX
    0.27
    æĸĩ
    0.26
    GRAM
    0.26
    testing
    0.25
    iverse
    0.24
    Sept
    0.24
     Jeb
    0.24
     Mex
    0.24
    OWL
    0.23
     Testing
    0.23
    Activations Density 0.252%

    No Known Activations