Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 27-TRANSCODER-HP
    4. 1022
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ñĥж
    -0.26
    подоб
    -0.26
     reun
    -0.26
     propri
    -0.25
     mood
    -0.25
     Important
    -0.25
    iez
    -0.25
    otive
    -0.24
    以为
    -0.23
    Bu
    -0.23
    POSITIVE LOGITS
    anus
    0.27
    hints
    0.25
    rei
    0.25
    eries
    0.25
     contacts
    0.24
    èµĦ
    0.24
    rais
    0.24
    anela
    0.24
     Fare
    0.24
    code
    0.24
    Activations Density 0.166%

    No Known Activations

    This feature has no known activations.