© 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. 39296
    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
     w
    -0.31
     d
    -0.31
     s
    -0.28
     ho
    -0.28
     X
    -0.28
    ?.
    -0.28
     z
    -0.27
     j
    -0.27
     Q
    -0.27
     h
    -0.27
    POSITIVE LOGITS
    iate
    0.28
    ssp
    0.27
    ripe
    0.27
    manifest
    0.26
    æĪIJçĨŁçļĦ
    0.25
     ë§Ī볨
    0.25
    ialized
    0.25
    ä¼Ŀ
    0.25
    æĪIJçĨŁ
    0.24
    anked
    0.24
    Activations Density 6.189%

    No Known Activations