© 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. 130303
    Prev
    Next
    INDEX
    Explanations

    Years and numbers

    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
    arrass
    -0.26
    eson
    -0.26
    aben
    -0.25
    ä¸Ģè´¯
    -0.25
    ä¼ijæģ¯
    -0.25
    æĺŁç©º
    -0.25
    alus
    -0.24
     Proposed
    -0.23
     neighbour
    -0.23
     interviews
    -0.23
    POSITIVE LOGITS
    ollah
    0.29
    æī¹éĩı
    0.29
     sür
    0.28
    uri
    0.28
    éĸ£
    0.27
    positor
    0.26
    ød
    0.26
    .readInt
    0.25
     Sk
    0.25
    æĸŃè£Ĥ
    0.25
    Activations Density 10.668%

    No Known Activations