© 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. 7004
    Prev
    Next
    INDEX
    Explanations

    (

    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
    EventArgs
    -0.24
    ilename
    -0.24
    cms
    -0.23
    Replacing
    -0.23
     Both
    -0.23
     replacing
    -0.23
    TextWriter
    -0.23
     Replace
    -0.23
     subtle
    -0.23
    Filename
    -0.23
    POSITIVE LOGITS
    æŀī
    0.30
    被éªĹ
    0.27
    åıĹå½±åĵį
    0.27
     swath
    0.26
    ilton
    0.26
    ercul
    0.25
    lost
    0.25
    Lost
    0.25
    aina
    0.25
    çĸµ
    0.24
    Activations Density 0.047%

    No Known Activations