© 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. 88641
    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
    æĿ¾å¼Ľ
    -0.26
    横
    -0.26
     اÙĦتش
    -0.24
    Word
    -0.24
     Word
    -0.24
     pet
    -0.24
    æľīç§į
    -0.24
    (Number
    -0.23
     tour
    -0.23
     WORD
    -0.23
    POSITIVE LOGITS
    级以ä¸Ĭ
    0.27
    -gradient
    0.25
    æī¾åĽŀ
    0.25
    éĥ½æĹłæ³ķ
    0.25
     grandson
    0.25
    -plane
    0.25
    æĬĹä½ĵ
    0.25
    å¤ĸè¯Ń
    0.25
    级
    0.25
    ências
    0.25
    Activations Density 2.421%

    No Known Activations

    This feature has no known activations.