© 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. 40255
    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
    åIJĮäºĭ们
    -0.29
    ihn
    -0.27
     periodic
    -0.27
     velocities
    -0.27
    pairs
    -0.26
    achts
    -0.26
    ells
    -0.26
     Case
    -0.25
     Hastings
    -0.25
     Cases
    -0.25
    POSITIVE LOGITS
    æijĺ
    0.28
    èĦļ
    0.27
    inger
    0.27
    æīĵæ³ķ
    0.26
    裸
    0.26
    grab
    0.26
     hacking
    0.26
     guerr
    0.26
     keynote
    0.25
    æĥ³
    0.25
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.