© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53804
    Prev
    Next
    INDEX
    Explanations

    Places in England

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mag
    -0.30
     Bam
    -0.27
     Beh
    -0.27
    ä¸į解
    -0.26
    å¤ķ
    -0.26
    èµĦæľ¬
    -0.25
    closest
    -0.25
    ç«Ļ
    -0.25
    æĻ¶
    -0.24
    mag
    -0.24
    POSITIVE LOGITS
    åĮĹè·¯
    0.26
    ornado
    0.26
    夷
    0.26
    ÑĪек
    0.25
    anity
    0.25
     Suit
    0.25
    çļĦæĶ¿æ²»
    0.24
    .setLevel
    0.24
     Sao
    0.24
     Lantern
    0.23
    Activations Density 0.023%

    No Known Activations