© 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. 89288
    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
    “At
    -0.26
    ’an
    -0.25
    -temp
    -0.25
    “As
    -0.25
    ä»ij
    -0.25
    绳
    -0.24
    “One
    -0.24
    çļĦçģµéŃĤ
    -0.24
    BITS
    -0.24
    ’en
    -0.24
    POSITIVE LOGITS
    è§ģéĿ¢
    0.26
    渣
    0.26
    è¿ĩ
    0.25
     oluÅŁtur
    0.25
     над
    0.25
     Hind
    0.25
     radio
    0.25
    转
    0.24
    åªĴä½ĵ
    0.24
    ullo
    0.24
    Activations Density 9.770%

    No Known Activations

    This feature has no known activations.