© 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. 108819
    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
    çī¹æľĹ
    -0.32
    elden
    -0.28
    ány
    -0.26
    hani
    -0.25
    oble
    -0.25
    æķ£åıij
    -0.25
    ignty
    -0.25
     szczegóÅĤowo
    -0.25
     QGraphics
    -0.24
     congratulations
    -0.24
    POSITIVE LOGITS
    æĶ¯
    0.33
    zone
    0.29
    Zone
    0.27
     Zone
    0.26
    ÙħÙĬÙĦ
    0.26
     zahl
    0.25
    æĶ¾
    0.25
    ÑĨ
    0.25
    çĻ¸
    0.24
     zone
    0.24
    Activations Density 0.065%

    No Known Activations

    This feature has no known activations.