© 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. 63329
    Prev
    Next
    INDEX
    Explanations

    Numbers and quantities

    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
    ambio
    -0.30
    Ber
    -0.28
     Ber
    -0.28
    éķ¿å¤§äºĨ
    -0.26
    åĪ°è¿ĻéĩĮ
    -0.25
     ramp
    -0.25
    .proto
    -0.25
    å¥ĩ
    -0.24
     arkadaÅŁ
    -0.24
    InputChange
    -0.23
    POSITIVE LOGITS
    éĽħ
    0.28
    åİļ
    0.27
    ugal
    0.27
    =edge
    0.26
    交
    0.26
    æݨ
    0.25
     globally
    0.25
     Thur
    0.25
    trä
    0.25
    GLOBALS
    0.24
    Activations Density 7.644%

    No Known Activations