© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 106961
    Prev
    Next
    INDEX
    Explanations

    code snippets or XML

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
    (schema
    -0.26
    èĢĮåĩº
    -0.25
    NET
    -0.25
    éģĹ
    -0.25
    缴åĪ°
    -0.25
     ÑĥÑģп
    -0.24
    .gold
    -0.24
    orsche
    -0.24
    ny
    -0.23
    orz
    -0.23
    POSITIVE LOGITS
    iment
    0.25
    ipient
    0.24
    çıłä¸īè§Ĵ
    0.24
    	me
    0.23
     outer
    0.23
    -turn
    0.23
    ä¸Ńå¤ĸ
    0.23
    ÑģÑĤвеннÑĭе
    0.23
    å·¥åķĨ
    0.23
    erving
    0.22
    Activations Density 0.951%

    No Known Activations