© 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. 109484
    Prev
    Next
    INDEX
    Explanations

    Abstract nouns and concepts

    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
    ãģ¨ãģªãĤĭ
    -0.25
     nature
    -0.25
    åįģ个
    -0.24
    ë°°
    -0.24
    ç¬Ķè®°æľ¬
    -0.24
    itone
    -0.24
    rito
    -0.24
    pha
    -0.24
     Cursor
    -0.23
     Iterator
    -0.23
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.35
     rather
    0.33
    èĢĮéĿŀ
    0.32
    ophobia
    0.30
    both
    0.29
     both
    0.28
    rather
    0.28
     BOTH
    0.27
    åıĮèµ¢
    0.27
    ä¸įä»ħä»ħæĺ¯
    0.26
    Activations Density 0.935%

    No Known Activations