© 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. 150623
    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
    ÑĢаÑī
    -0.26
    ÙĥÙĩ
    -0.25
     fitted
    -0.25
    æĮ½
    -0.25
    ulary
    -0.24
     limitation
    -0.23
    æĬķæĶ¾
    -0.23
    ings
    -0.23
    Seleccione
    -0.23
    plain
    -0.23
    POSITIVE LOGITS
    .ver
    0.28
    еб
    0.27
    åĬª
    0.25
    AZY
    0.25
    iteral
    0.25
    pcb
    0.24
     Trees
    0.24
    ç´§
    0.24
    å·´æĸ¯
    0.23
    ards
    0.23
    Activations Density 0.032%

    No Known Activations

    This feature has no known activations.