© 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. 39799
    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
    Dictionary
    -0.26
    çļĦ带é¢Ĩ
    -0.23
    Extract
    -0.23
    éªĦ
    -0.23
    æĨĤ
    -0.23
    :type
    -0.23
    Idle
    -0.23
     user
    -0.23
     cursed
    -0.23
     cubic
    -0.23
    POSITIVE LOGITS
    culus
    0.27
    åĪĨæĺİ
    0.25
    arme
    0.24
     Tup
    0.24
     Luc
    0.24
     Mate
    0.24
    cul
    0.24
    olini
    0.23
    érica
    0.23
    ture
    0.23
    Activations Density 52.390%

    No Known Activations

    This feature has no known activations.