© 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. 150230
    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
    æıIJæĹ©
    -0.28
     footing
    -0.27
    èĭĹ
    -0.26
    éģ½
    -0.24
    .prevent
    -0.24
    tick
    -0.24
    åŁºè°ĥ
    -0.24
     Tick
    -0.24
     !=↵
    -0.24
    çĽį
    -0.23
    POSITIVE LOGITS
     optimizing
    0.29
     optimization
    0.28
     optimized
    0.27
     optimize
    0.25
    optim
    0.25
     hoÅŁ
    0.25
    ween
    0.24
    ceived
    0.24
     witnessed
    0.24
     Boeh
    0.24
    Activations Density 0.152%

    No Known Activations

    This feature has no known activations.