© 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. 52993
    Prev
    Next
    INDEX
    Explanations

    learning, abilities

    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
    egot
    -0.32
    INVALID
    -0.30
    å«īå¦Ĵ
    -0.28
    ynos
    -0.28
    她说
    -0.27
    çīł
    -0.27
    lijke
    -0.26
    ,{"
    -0.26
    orra
    -0.26
    Èĺ
    -0.26
    POSITIVE LOGITS
     right
    0.53
     using
    0.49
    !
    0.42
     while
    0.40
    Right
    0.40
     by
    0.39
    using
    0.39
     Right
    0.39
     such
    0.39
    right
    0.38
    Activations Density 0.063%

    No Known Activations