© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 257
    Prev
    Next
    INDEX
    Explanations

    Åį

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Äħż
    -0.29
    <<<
    -0.24
    onto
    -0.24
    åľ¨èģĮ
    -0.24
    /opt
    -0.23
     Hy
    -0.23
    !/
    -0.23
     Re
    -0.23
    oyo
    -0.23
    ór
    -0.23
    POSITIVE LOGITS
    tion
    0.24
    iT
    0.24
    cot
    0.24
    election
    0.23
    Ĩµ
    0.23
    æĶ¶ç¼©
    0.23
    eam
    0.23
    enburg
    0.23
    cart
    0.23
    ging
    0.22
    Activations Density 0.009%

    No Known Activations