© 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. 35-TRANSCODER-HP
    7. 39208
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otle
    -0.31
    -educated
    -0.26
    itime
    -0.25
    setProperty
    -0.25
    RootElement
    -0.25
    åħ¶å®ĥéĹ®é¢ĺ
    -0.25
    createCommand
    -0.24
    AndView
    -0.24
    .DialogResult
    -0.24
    totals
    -0.24
    POSITIVE LOGITS
    1
    0.29
    '
    0.29
    å°ijäºĨ
    0.28
     '
    0.28
    2
    0.27
    å¿«
    0.27
     appropriate
    0.26
    '"
    0.26
     fully
    0.26
     **
    0.26
    Activations Density 59.582%

    No Known Activations

    This feature has no known activations.