© 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. 7652
    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
     prelim
    -0.30
    orno
    -0.30
    ingerprint
    -0.28
    secs
    -0.26
    _Field
    -0.26
    åī§
    -0.26
    bpp
    -0.26
    cratch
    -0.25
    inct
    -0.25
    éĺ²èħIJ
    -0.24
    POSITIVE LOGITS
    suite
    0.31
    uis
    0.29
    lik
    0.27
     contempor
    0.26
    çĥĬ
    0.26
    dit
    0.25
    iba
    0.25
     c
    0.25
    ber
    0.25
    ÏĢ
    0.25
    Activations Density 1.981%

    No Known Activations

    This feature has no known activations.