© 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. 107355
    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
    .nz
    -0.30
    ight
    -0.28
    oons
    -0.27
    åħīçĶµ
    -0.26
    缯
    -0.25
    éĴ¿
    -0.24
    ãĤ±ãĥĥãĥĪ
    -0.24
     breath
    -0.23
    éŃĦ
    -0.23
     зло
    -0.23
    POSITIVE LOGITS
    otoxic
    0.24
    è¶ĭ
    0.24
    cur
    0.24
     id
    0.23
    åŃĹåı·
    0.23
    .decor
    0.23
    [cur
    0.23
     pam
    0.23
    ôm
    0.23
    à®ļ
    0.23
    Activations Density 0.166%

    No Known Activations

    This feature has no known activations.