© 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. 7634
    Prev
    Next
    INDEX
    Explanations

    them

    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
    spiel
    -0.26
     course
    -0.26
    erd
    -0.26
    çĴ§
    -0.26
    購買
    -0.25
    egin
    -0.25
     dream
    -0.25
    åĪį
    -0.24
    ç¡®è¯ĬçĹħä¾ĭ
    -0.24
     bart
    -0.23
    POSITIVE LOGITS
    åį¡éĢļ
    0.26
     Público
    0.26
    ONO
    0.26
    éĽħ
    0.25
     Rehab
    0.25
    raries
    0.25
    ä¸īæĸ¹
    0.25
    æľīæķĪæĢ§
    0.24
    çļĦæľĢä½³
    0.24
    æľĢä½³
    0.24
    Activations Density 0.010%

    No Known Activations