© 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. 6848
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    olars
    -0.28
    ÑĥÑĢÑģ
    -0.27
    lection
    -0.25
    太éĺ³
    -0.24
    ied
    -0.24
    song
    -0.23
    spr
    -0.23
    å¯Ĵ
    -0.23
     TableRow
    -0.23
    s
    -0.23
    POSITIVE LOGITS
     alike
    0.25
    åİ»åĵªéĩĮ
    0.25
    è°ĥéħį
    0.25
    é®
    0.23
    æ´®
    0.23
    æĪij对
    0.23
     Laptop
    0.23
    éĴ¯
    0.23
    PMC
    0.23
    éªĪ
    0.23
    Activations Density 1.801%

    No Known Activations

    This feature has no known activations.