© 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. 39330
    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
     play
    -0.31
     conv
    -0.28
    inger
    -0.27
     pad
    -0.26
     context
    -0.26
     mut
    -0.26
     tro
    -0.26
     will
    -0.25
    conv
    -0.25
     integrate
    -0.25
    POSITIVE LOGITS
     lyon
    0.28
    ETCH
    0.25
    liest
    0.24
    æĿĨèıĮ
    0.24
    Defs
    0.24
    åıijå±ķ空éĹ´
    0.23
    icional
    0.23
    èļ´
    0.23
    åĨįåİ»
    0.23
    urate
    0.23
    Activations Density 50.339%

    No Known Activations

    This feature has no known activations.