© 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. 63187
    Prev
    Next
    INDEX
    Explanations

    park

    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
    åĪĺæµ·
    -0.27
    han
    -0.27
     reluct
    -0.27
    okens
    -0.27
    çģ«çĥ§
    -0.26
    obox
    -0.26
    æĸ°è¥¿
    -0.26
    olars
    -0.25
    hung
    -0.25
     VE
    -0.24
    POSITIVE LOGITS
    ä¸į足
    0.25
     Alternative
    0.24
    -strip
    0.24
    _async
    0.24
    emade
    0.23
    -chain
    0.23
     derechos
    0.23
    èĽ®
    0.23
    alternative
    0.23
     Autumn
    0.23
    Activations Density 6.972%

    No Known Activations