© 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. 107165
    Prev
    Next
    INDEX
    Explanations

    Text excerpts

    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
     transported
    -0.29
    æ»´
    -0.27
     spr
    -0.26
     Wir
    -0.26
     field
    -0.25
    $field
    -0.25
     mount
    -0.25
    çĪĨ
    -0.24
     awakening
    -0.24
    ä¸İæŶ
    -0.24
    POSITIVE LOGITS
     yearly
    0.29
     annual
    0.27
    eneral
    0.27
    icare
    0.26
    essional
    0.26
    CHIP
    0.25
    WithTag
    0.25
    ç¢į
    0.25
    èģĬ
    0.25
    çīĴ
    0.25
    Activations Density 45.137%

    No Known Activations