© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 9287
    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
    imately
    -0.24
    OffsetTable
    -0.24
     enrollment
    -0.23
    _thr
    -0.23
    rink
    -0.23
     scratch
    -0.22
    IJľ
    -0.22
     Composer
    -0.22
    è¿ĺåľ¨
    -0.22
    kos
    -0.22
    POSITIVE LOGITS
    OMPI
    0.26
    NES
    0.26
    饱åĴĮ
    0.25
    çĶij
    0.24
    åĬ¨çī©
    0.24
     Shed
    0.23
    æľ
    0.23
    recht
    0.23
    untu
    0.23
    gnore
    0.23
    Activations Density 1.752%

    No Known Activations

    This feature has no known activations.