© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6356
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    ué
    -0.27
    uos
    -0.27
     act
    -0.26
     {}.
    -0.26
    &q
    -0.25
    etri
    -0.25
    erea
    -0.25
    ssp
    -0.25
    (off
    -0.25
    è¿ĺæľī
    -0.25
    POSITIVE LOGITS
    æĪĴ
    0.29
    oney
    0.27
     understanding
    0.25
    讵
    0.25
    inox
    0.24
    ulu
    0.24
    IBUT
    0.23
    éĻIJ
    0.23
    æĹ¶æľº
    0.23
    åıĹå½±åĵį
    0.23
    Activations Density 0.012%

    No Known Activations