© 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. 6943
    Prev
    Next
    INDEX
    Explanations

    news articles

    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
    éģĹ
    -0.34
    æŃ»åİ»
    -0.34
    æŃ»
    -0.32
     dead
    -0.32
     funeral
    -0.32
    èij¬
    -0.32
     deceased
    -0.31
    æŃ»åIJİ
    -0.31
    cached
    -0.29
    æ®ģ
    -0.29
    POSITIVE LOGITS
     Revel
    0.26
    çĬĢ
    0.25
    .locals
    0.25
     habil
    0.25
    çħ
    0.25
     insecure
    0.24
    ery
    0.24
     zwykÅĤ
    0.24
    ullivan
    0.24
     Counts
    0.24
    Activations Density 0.026%

    No Known Activations