© 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. 89214
    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
    oho
    -0.33
    çĩĥ
    -0.31
     hơi
    -0.29
    roupon
    -0.29
    饮
    -0.26
    urd
    -0.25
    ahi
    -0.25
    æ±½
    -0.24
    宾客
    -0.24
    è¯ķé¢ĺ
    -0.24
    POSITIVE LOGITS
     Alta
    0.26
    invalidate
    0.24
     bell
    0.24
    Explanation
    0.24
     implements
    0.24
    amat
    0.23
    bell
    0.23
    -target
    0.23
    criptors
    0.23
    éĴŁ
    0.23
    Activations Density 1.414%

    No Known Activations

    This feature has no known activations.