© 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. 12-TRANSCODER-HP
    7. 22598
    Prev
    Next
    INDEX
    Explanations

    Legal, political, geography context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åįļæĸĩ
    -0.28
    éĺı
    -0.27
    èī²
    -0.26
    %(
    -0.26
    Moder
    -0.25
    기ëĬĶ
    -0.24
     bergen
    -0.24
    ä¸ĵæłı
    -0.24
    çĬģ
    -0.24
     Moder
    -0.23
    POSITIVE LOGITS
    .Assembly
    0.27
    éĿ¡
    0.27
    schlä
    0.26
    poke
    0.25
    rü
    0.25
    @index
    0.25
    鸯
    0.24
    chia
    0.24
    unched
    0.24
    Æ°á»Łng
    0.23
    Activations Density 0.000%

    No Known Activations