© 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. 30-TRANSCODER-HP
    7. 95901
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿Ļæł·çļĦè¯Ŀ
    -0.29
    idelity
    -0.26
     sang
    -0.25
    ring
    -0.25
    §è¡Į
    -0.25
     Ring
    -0.24
    resent
    -0.24
     Herm
    -0.23
    -ring
    -0.23
    .rstrip
    -0.23
    POSITIVE LOGITS
     Pey
    0.28
    esen
    0.27
    ibili
    0.26
     patron
    0.25
    ibi
    0.25
    soever
    0.25
    owie
    0.25
    Bes
    0.24
    umat
    0.24
    =value
    0.23
    Activations Density 0.882%

    No Known Activations

    This feature has no known activations.