© 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. 108876
    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
    mins
    -0.30
    åºķ
    -0.28
    Sans
    -0.25
    è¯Ŀ
    -0.25
     uns
    -0.25
    ANTE
    -0.24
     unt
    -0.24
    è·³
    -0.23
    oran
    -0.23
    å¤ı天
    -0.23
    POSITIVE LOGITS
     Invite
    0.26
    uits
    0.26
    INV
    0.25
     Alv
    0.25
    uit
    0.25
    iqu
    0.25
    ãģĵãģ¨ãģ§ãģĻ
    0.24
    å¾ģéĽĨ
    0.24
    ancel
    0.23
    使ä¹ĭ
    0.23
    Activations Density 0.905%

    No Known Activations

    This feature has no known activations.