© 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. 24-TRANSCODER-HP
    7. 150562
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interrupted
    -0.26
     Urs
    -0.26
    éĢıæ°Ķ
    -0.25
     med
    -0.25
    容å¿į
    -0.25
    UserCode
    -0.25
    åĶ§
    -0.24
    angi
    -0.24
    tering
    -0.24
    ovich
    -0.24
    POSITIVE LOGITS
     discrepancy
    0.26
    lein
    0.26
    bracht
    0.25
    <pre
    0.24
    lemen
    0.24
    inci
    0.24
    yled
    0.24
     correctly
    0.24
    沿
    0.23
    .databinding
    0.23
    Activations Density 0.015%

    No Known Activations

    This feature has no known activations.