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. 1-TRANSCODER-HP
    4. 63
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_1.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.1.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çķĮçļĦ
    -0.30
    ä¸ĢéŨ
    -0.30
    /cpu
    -0.26
    ä¸ĵçıŃ
    -0.25
     inevitable
    -0.25
    erce
    -0.25
    BUG
    -0.25
    CellValue
    -0.24
    cé
    -0.24
    èĥ¡
    -0.24
    POSITIVE LOGITS
    ï¼±
    0.29
    NSE
    0.28
    itol
    0.28
    letter
    0.26
     Charg
    0.25
    NotSupportedException
    0.25
    orgia
    0.24
    aldo
    0.24
    SizeMode
    0.24
     manip
    0.24
    Activations Density 37.439%

    No Known Activations

    This feature has no known activations.