© 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. 6045
    Prev
    Next
    INDEX
    Explanations

    0

    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
     prive
    -0.27
    culate
    -0.25
    gings
    -0.24
     nib
    -0.24
    parate
    -0.24
     diplom
    -0.24
    curity
    -0.24
     unsus
    -0.23
    formed
    -0.23
     disadv
    -0.23
    POSITIVE LOGITS
    å·®åĪ«
    0.28
    段
    0.27
    acet
    0.27
    abet
    0.26
    acus
    0.26
    äº¤æĽ¿
    0.26
    serrat
    0.26
    ĥģ
    0.26
    é£İ
    0.25
     ÅĽl
    0.25
    Activations Density 0.010%

    No Known Activations