© 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. 64114
    Prev
    Next
    INDEX
    Explanations

    Numbers and standards references

    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
    hip
    -0.27
    ESÄ°
    -0.25
     chain
    -0.25
    à¹Ī
    -0.25
    lichkeit
    -0.25
    <dd
    -0.25
    aller
    -0.24
     independent
    -0.24
    ç¼ĸ
    -0.24
    è¶ħ
    -0.23
    POSITIVE LOGITS
    sey
    0.26
    书åºĹ
    0.25
    æ±¾
    0.25
    æ®ĩ
    0.25
    壹
    0.25
    Concrete
    0.25
    fern
    0.24
    fos
    0.24
    ControlItem
    0.24
    æݬ
    0.24
    Activations Density 14.413%

    No Known Activations