© 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. 40064
    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
    ifar
    -0.26
    转åıĺ
    -0.25
     belief
    -0.25
    çı²
    -0.25
    datum
    -0.24
    éĢıæĺİ
    -0.23
     Clash
    -0.23
    æķıæĦŁ
    -0.23
    freeze
    -0.23
    iffe
    -0.23
    POSITIVE LOGITS
    Its
    0.25
    Tonight
    0.24
     вли
    0.24
     mockery
    0.23
    uzzer
    0.23
    awns
    0.23
    wk
    0.23
    -turned
    0.23
    Indented
    0.23
    çıī
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.