© 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. 53662
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
     landed
    -0.27
    lop
    -0.27
     m
    -0.26
    atoria
    -0.25
    .m
    -0.25
     distraction
    -0.24
     squeez
    -0.24
     Fortune
    -0.24
    issa
    -0.23
     chop
    -0.23
    POSITIVE LOGITS
    rit
    0.28
    /pub
    0.27
    cek
    0.26
    ä¸īæĿ¡
    0.26
    ools
    0.25
    çĤ¹æ»´
    0.25
    èĩ´
    0.25
    į°
    0.24
    ferred
    0.24
    ç¥ĸçĪ¶
    0.24
    Activations Density 0.008%

    No Known Activations