© 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. 6011
    Prev
    Next
    INDEX
    Explanations

    code, configs, documentation

    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
    agh
    -0.28
     Autor
    -0.26
    uen
    -0.26
     Approach
    -0.25
    ÑĢаг
    -0.25
    endoza
    -0.25
    _FREQUENCY
    -0.24
    alem
    -0.24
    agem
    -0.24
    ória
    -0.24
    POSITIVE LOGITS
    reat
    0.28
     carve
    0.27
    åħ¬çĶ¨
    0.26
    ä¸īç§į
    0.26
    hosts
    0.26
    ight
    0.26
    æīĢå¾Ĺ
    0.26
    éģŃ
    0.25
    sit
    0.25
    åħ¬ç½ij
    0.25
    Activations Density 0.030%

    No Known Activations