© 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
    2. Qwen3-4B
    3. 33-TRANSCODER-HP
    4. 53280
    Prev
    Next
    INDEX
    Explanations

    negative or foreign phrases

    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
     Lis
    -0.28
     li
    -0.27
    vais
    -0.27
    éĿ¢
    -0.26
     rich
    -0.26
     Archer
    -0.26
     wed
    -0.25
    ORITY
    -0.25
    çŀ§
    -0.25
     gaps
    -0.25
    POSITIVE LOGITS
    度è¿ĩ
    0.31
    acial
    0.28
    åħ³éŨ
    0.27
    æĽĻ
    0.26
     FIR
    0.26
    åħ»æĪIJ
    0.26
    icter
    0.26
    asser
    0.26
     displ
    0.25
    åĮĻ
    0.25
    Activations Density 0.010%

    No Known Activations