© 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. 150897
    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
    æ¯
    -0.27
    Compute
    -0.26
    丫
    -0.25
     hyp
    -0.25
     hypoth
    -0.24
    -eslint
    -0.24
    orer
    -0.24
    actus
    -0.23
     vulner
    -0.23
     completionHandler
    -0.23
    POSITIVE LOGITS
    nde
    0.30
    turnstile
    0.28
     tricks
    0.27
     Tricks
    0.26
    apia
    0.25
     castle
    0.25
     clips
    0.25
    ÑĪа
    0.24
    iable
    0.24
    æĮ«
    0.24
    Activations Density 0.136%

    No Known Activations

    This feature has no known activations.