© 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. 89136
    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
     practice
    -0.32
    rÃŃ
    -0.30
     practise
    -0.30
     ad
    -0.28
    ju
    -0.28
     orient
    -0.27
    aire
    -0.27
    å®ŀè·µ
    -0.27
     Grade
    -0.26
    _orient
    -0.26
    POSITIVE LOGITS
     fflush
    0.28
    åħ¥åľº
    0.26
    dead
    0.26
    eno
    0.26
    /Internal
    0.25
     imageSize
    0.25
    енно
    0.25
    ç¬ijè¯Ŀ
    0.24
     zza
    0.24
    subst
    0.24
    Activations Density 0.540%

    No Known Activations

    This feature has no known activations.