© 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. 7226
    Prev
    Next
    INDEX
    Explanations

    Measurements and data

    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
    è¡·
    -0.30
    iais
    -0.28
    æľ¬æľŁ
    -0.27
    Ø«ÙĦ
    -0.27
    åħĪåIJİ
    -0.27
    istani
    -0.26
    oles
    -0.26
    éĢĨ
    -0.25
    orre
    -0.25
    ä»ħä»ħ
    -0.25
    POSITIVE LOGITS
    cec
    0.31
     Feather
    0.30
     alignment
    0.25
    Wiki
    0.25
     survival
    0.24
     lab
    0.24
     Cec
    0.23
    åłĤ
    0.23
    .rs
    0.23
     Lab
    0.23
    Activations Density 0.018%

    No Known Activations