© 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. 8007
    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
     forwards
    -0.30
    使ä¹ĭ
    -0.28
     accelerating
    -0.27
     Sent
    -0.26
     eup
    -0.25
    Gap
    -0.25
    strand
    -0.25
    使åħ¶
    -0.25
    (up
    -0.25
    vier
    -0.25
    POSITIVE LOGITS
     JObject
    0.25
    pres
    0.24
    edom
    0.24
    éĬĢ
    0.24
     quyá»ģn
    0.24
    ulla
    0.23
    ëĮĢë¡ľ
    0.23
    ило
    0.23
    itti
    0.23
    aran
    0.23
    Activations Density 3.099%

    No Known Activations

    This feature has no known activations.