© 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. 130
    Prev
    Next
    INDEX
    Explanations

    Copenhagen

    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
    akedown
    -0.29
    èĮ±
    -0.28
     prescribed
    -0.28
    å¿«
    -0.28
     crisis
    -0.25
     fast
    -0.25
    æ³ķ
    -0.25
    å¦Ĥæŀľæĺ¯
    -0.25
    åĽºå®ļçļĦ
    -0.25
     unint
    -0.25
    POSITIVE LOGITS
    .Emit
    0.26
    èī¯æĢ§
    0.25
    projection
    0.25
    Projection
    0.25
     Provision
    0.24
    Resume
    0.24
    hana
    0.24
    足足
    0.23
    Strict
    0.23
    igne
    0.23
    Activations Density 0.010%

    No Known Activations