© 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. 40294
    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
    æĦıè§ģåıįé¦Ī
    -0.29
    çĶµä»·
    -0.28
     favoured
    -0.28
    ream
    -0.27
    è§Ĥå½±
    -0.27
     creo
    -0.27
     exceedingly
    -0.26
    è£Ĩ
    -0.26
     höch
    -0.26
    irq
    -0.25
    POSITIVE LOGITS
    Pro
    0.28
     Pro
    0.28
     гоÑĢ
    0.28
     Syn
    0.27
    ()?.
    0.26
     Bench
    0.26
     ??
    0.26
    ??
    0.25
     Stack
    0.25
    2
    0.25
    Activations Density 13.867%

    No Known Activations

    This feature has no known activations.