© 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. 40376
    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
    ä¹Łåıªæľī
    -0.31
    趣
    -0.28
    atures
    -0.27
     interes
    -0.27
    Others
    -0.26
    lund
    -0.26
    EE
    -0.26
     interest
    -0.26
    å°±æĬĬ
    -0.26
    ATURE
    -0.26
    POSITIVE LOGITS
    åĩı
    0.25
    éĩįç£ħ
    0.25
    åħ«å¤§
    0.25
     testing
    0.25
     Frag
    0.25
     Federation
    0.24
    座è°Īä¼ļä¸Ĭ
    0.24
     tracking
    0.23
     conditioning
    0.23
     mechanical
    0.23
    Activations Density 0.012%

    No Known Activations

    This feature has no known activations.