© 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. 39742
    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
    é¼¾
    -0.31
     bu
    -0.29
     UEFA
    -0.27
     König
    -0.26
    æī¼
    -0.26
    occer
    -0.26
    ocrates
    -0.24
    æĪĸå¤ļ
    -0.24
    ngrx
    -0.24
     maneuver
    -0.24
    POSITIVE LOGITS
    ase
    0.31
    ais
    0.29
    ayan
    0.28
    å²Ľ
    0.26
    omin
    0.26
    ane
    0.25
    ile
    0.25
    è¡«
    0.25
    1
    0.25
    are
    0.25
    Activations Density 9.462%

    No Known Activations

    This feature has no known activations.