© 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. 25-TRANSCODER-HP
    7. 108075
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ág
    -0.24
    æ¹¾åĮº
    -0.24
     Concurrent
    -0.24
     Corner
    -0.24
    åħĪæĬĬ
    -0.23
    quarter
    -0.23
    çļĭ
    -0.23
    访
    -0.23
    Textures
    -0.23
    æĿijåºĦ
    -0.23
    POSITIVE LOGITS
    piece
    0.31
     piece
    0.27
    件
    0.26
    '
    0.26
    DK
    0.25
    _piece
    0.25
    dra
    0.25
    磼
    0.25
    æĬķæłĩ人
    0.24
     paced
    0.24
    Activations Density 0.149%

    No Known Activations

    This feature has no known activations.