© 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. 149676
    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
    转åĮĸ
    -0.29
     conversions
    -0.26
    è¶ĭ
    -0.26
     convergence
    -0.25
    pered
    -0.25
    icester
    -0.25
    ign
    -0.25
    ned
    -0.24
    arov
    -0.24
    HEMA
    -0.24
    POSITIVE LOGITS
    éģij
    0.27
    çİĩ为
    0.26
     pads
    0.26
    ÑĮев
    0.25
     Belfast
    0.25
     Pittsburgh
    0.25
    pled
    0.25
    ather
    0.24
    inalg
    0.24
    æĬij
    0.24
    Activations Density 1.168%

    No Known Activations

    This feature has no known activations.