© 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. 6864
    Prev
    Next
    INDEX
    Explanations

    Technical documents, code, academic papers

    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
    uf
    -0.29
     nuisance
    -0.27
    -ins
    -0.27
     fil
    -0.26
     ÙĨÙĤ
    -0.25
    jay
    -0.24
    enums
    -0.24
     coordination
    -0.23
    å®ģåİ¿
    -0.23
    -shell
    -0.23
    POSITIVE LOGITS
    Aligned
    0.29
    ç½ijæ°ij
    0.26
    åĿ¨
    0.25
    å¯Ħ
    0.25
    retch
    0.25
    istrate
    0.25
    Initializer
    0.25
     Gale
    0.24
     tide
    0.24
    è¦ģ好好
    0.23
    Activations Density 0.003%

    No Known Activations