© 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. 109369
    Prev
    Next
    INDEX
    Explanations

    instead

    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
    éĻ¤äºĨ
    -0.29
    agnostic
    -0.28
    ugin
    -0.28
    uzzle
    -0.27
    åĪ°åºķ
    -0.27
    ä¹ĭä½Ļ
    -0.27
     nouve
    -0.26
     gerne
    -0.25
    éĻ¤
    -0.25
    ãģ¸
    -0.24
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.35
     rather
    0.35
     instead
    0.34
    èĢĮéĿŀ
    0.33
    instead
    0.33
    Instead
    0.27
     Rather
    0.26
    è§Ĭ
    0.26
    rather
    0.26
    Rather
    0.26
    Activations Density 0.999%

    No Known Activations