© 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. 150338
    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
    稿
    -0.28
    å¦ĵ
    -0.27
    ä»Ģ
    -0.27
    å¹Ĥ
    -0.27
    èīºæľ¯åĵģ
    -0.25
    ">%
    -0.24
    ainment
    -0.24
    eteria
    -0.23
    è¾ħ
    -0.23
    elfare
    -0.23
    POSITIVE LOGITS
    çĽ²çĽ®
    0.27
    (QL
    0.27
    åĽłä¸ºæĪij们
    0.24
    é¼į
    0.24
     blanco
    0.24
    gré
    0.23
    uae
    0.23
    åģľæ»ŀ
    0.23
     prefixes
    0.23
    _sender
    0.23
    Activations Density 0.138%

    No Known Activations

    This feature has no known activations.