© 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. 107557
    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
    宿
    -0.28
    ÑĪение
    -0.27
    banks
    -0.26
    æ¯ģ
    -0.26
    istique
    -0.25
    声éģĵ
    -0.25
    åįľ
    -0.24
    uste
    -0.24
    åĤ¬
    -0.24
    heed
    -0.24
    POSITIVE LOGITS
    eor
    0.30
    EMA
    0.29
     spons
    0.28
    EOS
    0.28
    å½¹
    0.27
    liner
    0.26
    Fluid
    0.25
     Fluid
    0.25
    ç¼ľ
    0.25
    毫ä¸į
    0.25
    Activations Density 0.895%

    No Known Activations

    This feature has no known activations.