© 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. 141344
    Prev
    Next
    INDEX
    Explanations

    Machine-generated text

    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
    被æī§è¡Į
    -0.31
     executions
    -0.27
    .fp
    -0.27
    è¥Ħ
    -0.26
     fall
    -0.26
    ksam
    -0.26
     executing
    -0.25
     #:
    -0.25
     execute
    -0.24
     execution
    -0.24
    POSITIVE LOGITS
    ãĤıãģij
    0.26
    饥饿
    0.25
    oub
    0.23
    çķıæĥ§
    0.23
    ="[
    0.23
    _CY
    0.23
    .Interfaces
    0.23
    _pet
    0.23
    Tim
    0.22
    hoe
    0.22
    Activations Density 10.347%

    No Known Activations