© 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. 326
    Prev
    Next
    INDEX
    Explanations

    regulations

    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
    plus
    -0.29
    idot
    -0.25
    éĩĮæĸ¯
    -0.25
    ç»´æĬ¤
    -0.25
    ="--
    -0.23
    pery
    -0.23
    otive
    -0.23
     freedoms
    -0.23
    éĶ¢
    -0.22
    缴纳
    -0.22
    POSITIVE LOGITS
    âį¨
    0.26
    .PO
    0.26
    (end
    0.25
    Éij
    0.24
    aping
    0.24
    æĪ·
    0.23
    _imag
    0.23
    _PICK
    0.22
    串
    0.22
    über
    0.22
    Activations Density 0.044%

    No Known Activations