© 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. 149782
    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
    /MIT
    -0.28
     ~(
    -0.27
     '\''
    -0.26
    urally
    -0.25
    mitter
    -0.24
    åĪģ
    -0.24
    ovsky
    -0.23
     вок
    -0.23
    å°¤
    -0.23
    追究
    -0.23
    POSITIVE LOGITS
    xing
    0.29
     translators
    0.26
    è£ħ
    0.26
    è¾Ī
    0.25
    ä¸ĭä¸Ģ代
    0.25
    qualified
    0.25
    对æѤ
    0.25
     Arbit
    0.24
     planned
    0.24
    çIJĨæĥ³
    0.24
    Activations Density 0.088%

    No Known Activations

    This feature has no known activations.