© 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. 53985
    Prev
    Next
    INDEX
    Explanations

    Text fragments

    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
    å®ļéĩı
    -0.28
    ondo
    -0.28
    æ±Ĺ
    -0.28
    æ·Ģ
    -0.27
     disp
    -0.26
    ë¶Ī
    -0.26
    -html
    -0.26
     War
    -0.25
    èµİ
    -0.25
    èķ
    -0.24
    POSITIVE LOGITS
    座æ¤ħ
    0.27
    ophage
    0.27
    pmat
    0.26
     Rece
    0.25
    lier
    0.25
    ichi
    0.25
    RowIndex
    0.25
    OTO
    0.25
    lie
    0.25
     exits
    0.24
    Activations Density 0.012%

    No Known Activations