© 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. 31-TRANSCODER-HP
    7. 19502
    Prev
    Next
    INDEX
    Explanations

    August

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uent
    -0.28
    du
    -0.26
    .u
    -0.26
    duce
    -0.25
    lying
    -0.25
    Fu
    -0.25
    æ´Ļ
    -0.25
    èİ«æĸ¯
    -0.24
    ousse
    -0.24
     fluent
    -0.24
    POSITIVE LOGITS
    inger
    0.30
    enic
    0.28
     Cata
    0.27
    å®ī
    0.26
    å¸Ń
    0.26
    éģĵçIJĨ
    0.25
    Wonder
    0.25
     Ginger
    0.25
    URA
    0.24
    igans
    0.24
    Activations Density 0.004%

    No Known Activations