© 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. 109530
    Prev
    Next
    INDEX
    Explanations

    determine

    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
     poc
    -0.26
    ildo
    -0.26
     trusts
    -0.24
    ocratic
    -0.24
    Episode
    -0.24
    导读
    -0.24
     Luc
    -0.24
    .mock
    -0.23
    .look
    -0.23
     Cast
    -0.23
    POSITIVE LOGITS
     ::::::::
    0.27
    éľĢè¦ģçĶ¨
    0.27
     phạm
    0.26
    edb
    0.26
    ä»ĸ们çļĦ
    0.26
    ä½łéľĢè¦ģ
    0.26
    产ä¸ļç»ĵæŀĦ
    0.25
    ç®ĹäºĨ
    0.24
    产çĶŁäºĨ
    0.24
    çķĻä¸ĭäºĨ
    0.24
    Activations Density 1.029%

    No Known Activations