© 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. 39810
    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
    arine
    -0.24
    illion
    -0.23
    -tax
    -0.22
     yıllık
    -0.22
    義
    -0.21
    issan
    -0.21
     Designer
    -0.21
    大家åĪĨ享
    -0.21
    éĺµ
    -0.20
    人çļĦ
    -0.20
    POSITIVE LOGITS
    tement
    0.29
    ++++
    0.25
    ä¸ŃåİŁ
    0.24
    éĺ¿å¯Į
    0.24
    enaire
    0.23
    udit
    0.22
    transparent
    0.22
    åĺ¹
    0.22
    lage
    0.22
    nost
    0.22
    Activations Density 7.212%

    No Known Activations

    This feature has no known activations.