© 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. 89878
    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
    çĪ½
    -0.26
    erce
    -0.25
    ville
    -0.25
    idd
    -0.24
    imest
    -0.24
    icom
    -0.24
    ithe
    -0.24
    -stack
    -0.24
    icate
    -0.24
    castle
    -0.24
    POSITIVE LOGITS
    æĭĺ
    0.30
    .matcher
    0.28
    æįĤ
    0.26
    ä½ķå¤Ħ
    0.26
    ä¸Ģå¤Ħ
    0.26
    åĶ¤éĨĴ
    0.25
    oundation
    0.24
    æīŃæĽ²
    0.24
    èģĶéĢļ
    0.24
    Marsh
    0.23
    Activations Density 4.043%

    No Known Activations

    This feature has no known activations.