© 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. 88843
    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
    ød
    -0.28
     RN
    -0.28
    aminer
    -0.28
    оÑģÑĮ
    -0.27
    oise
    -0.27
    ä¸Ńå±±
    -0.27
     defense
    -0.25
    PRESSION
    -0.25
    åłħ
    -0.25
     Replies
    -0.25
    POSITIVE LOGITS
     sucks
    0.28
    Predict
    0.28
    eric
    0.27
     Predict
    0.27
    stile
    0.26
    çļĦçĭ¬çī¹
    0.26
    æĽ¿ä»£
    0.25
     predicts
    0.25
     exposures
    0.25
    nost
    0.25
    Activations Density 32.436%

    No Known Activations

    This feature has no known activations.