© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7048
    Prev
    Next
    INDEX
    Explanations

    Multiplication and factors

    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
     spectacle
    -0.27
    stras
    -0.26
    ugo
    -0.26
    &e
    -0.23
    æİĮ
    -0.23
     Caj
    -0.23
    ä¸Ģ线
    -0.23
    沿线
    -0.22
     obligation
    -0.22
    åĬłä»¥
    -0.22
    POSITIVE LOGITS
    å¾Ĺä½ı
    0.27
    å¾Ĺèµ·
    0.26
    ç¾½
    0.26
    éĶIJ
    0.25
     r
    0.25
    1
    0.25
    ager
    0.25
    åĬłå¿«
    0.25
    ç»Ī身
    0.25
    ew
    0.25
    Activations Density 0.130%

    No Known Activations