© 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. 39324
    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
    å¾Īæĸ¹ä¾¿
    -0.24
     lurking
    -0.24
     sticky
    -0.24
    -parts
    -0.24
     hoped
    -0.23
    sticky
    -0.23
     halves
    -0.23
     inconvenience
    -0.23
    -normal
    -0.22
    acher
    -0.22
    POSITIVE LOGITS
     Gest
    0.25
    ËĬ
    0.24
     Ãĸzel
    0.24
    ãģ¾ãĤĮ
    0.24
    Wh
    0.24
     Wh
    0.24
    æĢ§åij½
    0.24
     Rev
    0.23
     Imm
    0.23
    åij½
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.