© 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. 109575
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    ç±į
    -0.27
     alleg
    -0.26
    èĩªçĶ±
    -0.25
    hard
    -0.25
    è¿·æĥij
    -0.24
     Instructions
    -0.24
    tent
    -0.24
    éĻĦ
    -0.24
    ÑĤÑĮ
    -0.24
    å®Ī
    -0.24
    POSITIVE LOGITS
    弩
    0.30
    slash
    0.28
    ragments
    0.28
    quals
    0.27
    aven
    0.27
    imately
    0.27
    çĵ®
    0.26
    ä¸Ĭæĺł
    0.26
     DRIVE
    0.25
    çĻ»
    0.25
    Activations Density 1.357%

    No Known Activations