© 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. 53862
    Prev
    Next
    INDEX
    Explanations

    weight loss

    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
    utt
    -0.29
    åĮħ
    -0.28
    pat
    -0.28
     cum
    -0.27
    ean
    -0.26
    -m
    -0.26
     pat
    -0.26
    iceps
    -0.26
    ıģı
    -0.26
    éĽĨ
    -0.25
    POSITIVE LOGITS
     jp
    0.27
     Monetary
    0.26
    öl
    0.25
    asString
    0.25
    atorial
    0.25
    åĪ©çī©
    0.25
    /weather
    0.25
    estr
    0.25
    urette
    0.24
    éĹ´æİ¥
    0.24
    Activations Density 0.040%

    No Known Activations