© 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. 20-TRANSCODER-HP
    7. 129547
    Prev
    Next
    INDEX
    Explanations

    Numbers, percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åIJĥå¾Ĺ
    -0.25
    anken
    -0.25
    riors
    -0.25
    anky
    -0.25
    enet
    -0.24
    éªĭ
    -0.24
    artment
    -0.24
    ç§ģæľį
    -0.24
    .SIZE
    -0.24
    DITION
    -0.23
    POSITIVE LOGITS
     major
    0.26
    _tem
    0.26
     commission
    0.26
    tem
    0.26
     und
    0.25
    æ£ł
    0.25
     incor
    0.24
     But
    0.24
    commission
    0.24
     rep
    0.24
    Activations Density 1.732%

    No Known Activations