© 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. 40183
    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
    ombres
    -0.28
    osterone
    -0.27
    ersist
    -0.26
    icts
    -0.26
    ialog
    -0.25
    _ordered
    -0.24
    itches
    -0.24
    atch
    -0.24
    odies
    -0.23
    atories
    -0.23
    POSITIVE LOGITS
     lower
    0.33
     process
    0.33
    æ¯Ķ
    0.28
    å®ļ
    0.27
    æģ°
    0.26
     reusable
    0.26
    æģ°å¥½
    0.26
     fixed
    0.26
    è¾ĥä½İ
    0.26
     pi
    0.25
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.