© 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. 142304
    Prev
    Next
    INDEX
    Explanations

    Code/licenses

    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
     {_
    -0.27
     besides
    -0.26
     Roller
    -0.26
     lite
    -0.25
     Arbitrary
    -0.25
    èĢģ大
    -0.24
    opal
    -0.24
    ihat
    -0.24
     Any
    -0.23
    axter
    -0.23
    POSITIVE LOGITS
    æŃ£
    0.29
    å°Ĩåħ¶
    0.29
    åħ¸åŀĭ
    0.27
    èĥľ
    0.25
    ”çļĦ
    0.25
    å®ĮæĪIJåIJİ
    0.25
    æĺĵ
    0.25
    æŀģé«ĺ
    0.25
    .Slf
    0.24
    (strict
    0.24
    Activations Density 2.015%

    No Known Activations