© 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. 19-TRANSCODER-HP
    7. 6414
    Prev
    Next
    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iaux
    -0.33
    pper
    -0.28
     trailers
    -0.28
    åĪĨè¡Į
    -0.27
     catch
    -0.26
    num
    -0.26
    ping
    -0.26
    bis
    -0.26
     `
    -0.25
    ignon
    -0.25
    POSITIVE LOGITS
    eds
    0.27
    stance
    0.26
    esome
    0.25
    erce
    0.24
    ctrine
    0.24
    taire
    0.24
    @foreach
    0.23
    åĪĽéĢłäºĨ
    0.23
    баÑĢ
    0.23
    arta
    0.23
    Activations Density 0.103%

    No Known Activations