© 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. 18-TRANSCODER-HP
    7. 89666
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»ĸ认为
    -0.27
    iest
    -0.25
    iated
    -0.25
    aji
    -0.25
    bit
    -0.24
    loid
    -0.24
    gp
    -0.24
    èĢģ人家
    -0.24
    ium
    -0.24
     filament
    -0.24
    POSITIVE LOGITS
    å¤ĩ
    0.31
    aub
    0.29
     land
    0.28
    ivos
    0.28
    ube
    0.27
    åıij
    0.26
    ères
    0.25
    asco
    0.24
    ves
    0.24
    ropa
    0.24
    Activations Density 2.438%

    No Known Activations

    This feature has no known activations.